docs(skill): plain wording for the unclear-chain case

For a transitive package the caller of the affected API is the package one
hop above it on each chain (body-parser for express > body-parser > qs),
not the direct dependency. Inspect that package on every chain; any chain
left unclear keeps the finding at imported.

containers/Dockerfile

@@ -186,13 +186,27 @@ RUN set -eux; \
         aarch64|arm64) GITLEAKS_ARCH="arm64" ;; \
         *) echo "Unsupported architecture: $ARCH" >&2; exit 1 ;; \
     esac; \
-    TAG="$(curl -fsSL https://api.github.com/repos/gitleaks/gitleaks/releases/latest | jq -r .tag_name)"; \
+    TAG="$(curl -fsSLI -o /dev/null -w '%{url_effective}' https://github.com/gitleaks/gitleaks/releases/latest | sed 's#.*/##')"; \
     curl -fsSL "https://github.com/gitleaks/gitleaks/releases/download/${TAG}/gitleaks_${TAG#v}_linux_${GITLEAKS_ARCH}.tar.gz" -o /tmp/gitleaks.tgz; \
     tar -xzf /tmp/gitleaks.tgz -C /tmp; \
     install -m 0755 /tmp/gitleaks /usr/local/bin/gitleaks; \
     rm -f /tmp/gitleaks /tmp/gitleaks.tgz
 
-RUN curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh | sh -s -- -b /usr/local/bin
+ARG TRIVY_VERSION=0.76.1
+ARG TRIVY_SHA256_X86=c7cbe3137fb8a48a17574bede3dd6beb16742d1e9772929940fc90082c39d9c0
+ARG TRIVY_SHA256_AARCH64=e174dff2a6dba5e3ae41f8d0537a6324405bd08132497340304c6b20e0f16a1f
+RUN set -eux; \
+    case "$(uname -m)" in \
+        x86_64) TRIVY_ARCH="64bit"; TRIVY_SHA256="${TRIVY_SHA256_X86}" ;; \
+        aarch64|arm64) TRIVY_ARCH="ARM64"; TRIVY_SHA256="${TRIVY_SHA256_AARCH64}" ;; \
+        *) echo "Unsupported architecture: $(uname -m)" >&2; exit 1 ;; \
+    esac; \
+    curl -fsSL "https://github.com/aquasecurity/trivy/releases/download/v${TRIVY_VERSION}/trivy_${TRIVY_VERSION}_Linux-${TRIVY_ARCH}.tar.gz" -o /tmp/trivy.tgz; \
+    echo "${TRIVY_SHA256}  /tmp/trivy.tgz" | sha256sum -c -; \
+    tar -xzf /tmp/trivy.tgz -C /tmp trivy; \
+    install -m 0755 /tmp/trivy /usr/local/bin/trivy; \
+    rm -f /tmp/trivy /tmp/trivy.tgz; \
+    trivy --version
 
 RUN apt-get install -y wapiti
 
@@ -212,10 +226,44 @@ RUN set -eux; \
     test "$(dpkg-query -W -f='${Version}' libbrotli1)" = "${BROTLI_DEB_VERSION}"; \
     node -e 'const z=require("zlib");z.brotliDecompressSync(z.brotliCompressSync(Buffer.from("ok")))'
 
+ARG OPENGREP_VERSION=1.31.0
+ARG OPENGREP_SHA256_X86=dbbe3c2058dbe600c449a8ba22ea79a1643a6660658400090d0323a8d0d31147
+ARG OPENGREP_SHA256_AARCH64=2b713a29a00237f85408b83002fc111db5b94c7fa8d263f0a93184a960655d9d
+RUN set -eux; \
+    case "$(uname -m)" in \
+        x86_64) OPENGREP_ARCH="x86"; OPENGREP_SHA256="${OPENGREP_SHA256_X86}" ;; \
+        aarch64|arm64) OPENGREP_ARCH="aarch64"; OPENGREP_SHA256="${OPENGREP_SHA256_AARCH64}" ;; \
+        *) echo "Unsupported architecture: $(uname -m)" >&2; exit 1 ;; \
+    esac; \
+    curl -fsSL "https://github.com/opengrep/opengrep/releases/download/v${OPENGREP_VERSION}/opengrep_manylinux_${OPENGREP_ARCH}" -o /tmp/opengrep; \
+    echo "${OPENGREP_SHA256}  /tmp/opengrep" | sha256sum -c -; \
+    install -m 0755 /tmp/opengrep /usr/local/bin/opengrep; \
+    rm -f /tmp/opengrep; \
+    opengrep --version
+
+# Opengrep ships no rule registry of its own; bake the community ruleset so
+# scans run offline. Keep only rule YAML and LICENSE; drop tests, fixtures,
+# tooling, and rules marked with a proprietary license.
+ARG OPENGREP_RULES_REF=f1d2b562b414783763fd02a6ed2736eaed622efa
+RUN set -eux; \
+    mkdir -p /opt/opengrep-rules; \
+    curl -fsSL "https://codeload.github.com/opengrep/opengrep-rules/tar.gz/${OPENGREP_RULES_REF}" \
+        | tar -xz --strip-components=1 -C /opt/opengrep-rules; \
+    cd /opt/opengrep-rules; \
+    rm -rf .github scripts stats; \
+    find . -maxdepth 1 -type f ! -name LICENSE -delete; \
+    find . -mindepth 2 -type f \( ! \( -name '*.yaml' -o -name '*.yml' \) -o -name '*.test.yaml' -o -name '*.test.yml' -o -name '.*' \) -delete; \
+    grep -rlZ 'license: proprietary' . | xargs -0 -r rm -f; \
+    find . -type d -empty -delete; \
+    chmod -R a+rX /opt/opengrep-rules
+
+# Strix-authored rules that close gaps in the community ruleset.
+COPY containers/opengrep-rules/ /opt/opengrep-rules/strix/
+RUN chmod -R a+rX /opt/opengrep-rules/strix
+
 USER pentester
 
-RUN pipx install semgrep && \
-    pipx install bandit
+RUN pipx install bandit
 
 RUN npm install -g jshint
 

containers/opengrep-rules/github-owned-action-not-pinned-to-commit-sha.yaml

@@ -0,0 +1,37 @@
+rules:
+  - id: github-owned-action-not-pinned-to-commit-sha
+    patterns:
+      - pattern-inside: "{steps: ...}"
+      - pattern: |
+          uses: "$USES"
+      - metavariable-regex:
+          metavariable: $USES
+          regex: '^(actions|github)/'
+      - metavariable-pattern:
+          metavariable: $USES
+          language: generic
+          patterns:
+            - pattern-not-regex: "@[0-9a-f]{40}$"
+    message: >-
+      GitHub-owned action `$USES` is referenced by a mutable tag or branch
+      instead of a full-length commit SHA. Tags can be moved, so a compromised
+      or force-pushed release changes what this workflow runs. Pin to the
+      commit SHA of the release you reviewed and let a bot keep it current.
+    languages:
+      - yaml
+    severity: WARNING
+    metadata:
+      cwe:
+        - "CWE-1357: Reliance on Insufficiently Trustworthy Component"
+        - "CWE-353: Missing Support for Integrity Check"
+      owasp: A06:2021 - Vulnerable and Outdated Components
+      references:
+        - https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-third-party-actions
+      category: security
+      technology:
+        - github-actions
+      subcategory:
+        - vuln
+      likelihood: LOW
+      impact: LOW
+      confidence: HIGH

docs/advanced/configuration.mdx

@@ -186,7 +186,7 @@ When remote vars are set, Strix dual-writes telemetry to both local JSONL and th
 
 ## Docker Configuration
 
-<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.3.1" type="string">
+<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.4.0" type="string">
   Docker image to use for the sandbox container.
 </ParamField>
 

docs/tools/sandbox.mdx

@@ -49,7 +49,7 @@ Strix runs inside a Kali Linux-based Docker container with a comprehensive set o
 
 | Tool                                                    | Description                                   |
 | ------------------------------------------------------- | --------------------------------------------- |
-| [Semgrep](https://github.com/semgrep/semgrep)          | Fast SAST and custom rule matching            |
+| [Opengrep](https://github.com/opengrep/opengrep)        | Fast SAST and custom rule matching            |
 | [ast-grep](https://ast-grep.github.io)                 | Structural AST/CST-aware code search (`sg`)   |
 | [Tree-sitter](https://tree-sitter.github.io/tree-sitter/) | Syntax tree parsing and symbol extraction (Java/JS/TS/Python/Go/Bash/JSON/YAML grammars pre-configured) |
 | [Bandit](https://bandit.readthedocs.io)                | Python security linter                        |

docs/tools/terminal.mdx

@@ -33,7 +33,7 @@ sqlmap -u "https://example.com/page?id=1"
 
 ```bash
 # Fast SAST triage
-semgrep --config auto ./src
+opengrep scan --config /opt/opengrep-rules ./src
 
 # Structural AST search
 sg scan ./src

docs/usage/scan-modes.mdx

@@ -46,7 +46,7 @@ Thorough penetration testing. Best for:
 
 **Duration**: 1-4 hours depending on target complexity
 
-**White-box behavior**: Runs broad source-aware triage (`semgrep`, AST structural search, secrets, supply-chain checks) and then systematically validates top candidates dynamically.
+**White-box behavior**: Runs broad source-aware triage (`opengrep`, AST structural search, secrets, supply-chain checks) and then systematically validates top candidates dynamically.
 
 <Note>
 Deep mode is the default. It explores edge cases, chained vulnerabilities, and complex attack paths.

scripts/install.sh

@@ -4,7 +4,7 @@ set -euo pipefail
 
 APP=strix
 REPO="usestrix/strix"
-STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.3.1"
+STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.4.0"
 
 MUTED='\033[0;2m'
 RED='\033[0;31m'

strix/agents/prompts/system_prompt.jinja

@@ -115,11 +115,11 @@ BLACK-BOX TESTING (domain/subdomain only):
 
 WHITE-BOX TESTING (code provided):
 - MUST perform BOTH static AND dynamic analysis
-- Static: Use source-aware triage first to map risk quickly (`semgrep`, `ast-grep`, Tree-sitter tooling, `gitleaks`, `trufflehog`, `trivy fs`). Then review code for vulnerabilities
+- Static: Use source-aware triage first to map risk quickly (`opengrep`, `ast-grep`, Tree-sitter tooling, `gitleaks`, `trufflehog`, `trivy fs`). Then review code for vulnerabilities
 - Static coverage floor: execute at least one structural AST mapping pass (`sg` and/or Tree-sitter) per repository and keep artifact output
-- Static coverage target per repository: run one `semgrep` pass, one secrets pass (`gitleaks` and/or `trufflehog`), one `trivy fs` pass, and one AST-structural pass (`sg` and/or Tree-sitter)
+- Static coverage target per repository: run one `opengrep` pass, one secrets pass (`gitleaks` and/or `trufflehog`), one `trivy fs` pass, and one AST-structural pass (`sg` and/or Tree-sitter)
 - Keep AST artifacts bounded and high-signal: scope to relevant paths/hypotheses, avoid whole-repo generic function dumps
-- AST target selection rule: build `sg-targets.txt` from `semgrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`), then run `xargs ... sg run` against that file list. Only use path-heuristic fallback if semgrep scope is unavailable.
+- AST target selection rule: build `sg-targets.txt` from `opengrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`), then run `xargs ... sg run` against that file list. Only use path-heuristic fallback if opengrep scope is unavailable.
 - Dynamic: Run the application and test live to validate exploitability
 - NEVER rely solely on static code analysis when dynamic validation is possible
 - Begin with fast source triage and dynamic run preparation in parallel; use static findings to prioritize live testing.
@@ -188,7 +188,7 @@ EFFICIENCY TACTICS:
 - For Caido proxy automation inside Python, explicitly import from
   `caido_api`:
   `from caido_api import list_requests, view_request, repeat_request, list_sitemap, view_sitemap_entry, scope_rules`
-- Prefer established fuzzers/scanners where applicable: ffuf, sqlmap, nuclei, wapiti, arjun, httpx, katana, semgrep, bandit, trufflehog, nmap. Use scripts mainly to coordinate or validate around them, not to replace them without reason
+- Prefer established fuzzers/scanners where applicable: ffuf, sqlmap, nuclei, wapiti, arjun, httpx, katana, opengrep, bandit, trufflehog, nmap. Use scripts mainly to coordinate or validate around them, not to replace them without reason
 - For trial-heavy vectors (SQLi, XSS, XXE, SSRF, RCE, auth/JWT, deserialization), DO NOT iterate payloads manually in the browser. Always spray payloads via Python scripts through `exec_command` or terminal tools.
 - When using established fuzzers/scanners, use the proxy for inspection where helpful
 - Generate/adapt large payload corpora: combine encodings (URL, unicode, base64), comment styles, wrappers, time-based/differential probes. Expand with wordlists/templates
@@ -458,7 +458,7 @@ JAVASCRIPT ANALYSIS:
 - js-beautify - JS beautifier/deobfuscator
 
 CODE ANALYSIS:
-- semgrep - Static analysis/SAST
+- opengrep - Static analysis/SAST (bundled rules in /opt/opengrep-rules)
 - ast-grep (sg) - Structural AST/CST-aware code search
 - tree-sitter - Syntax-aware parsing and symbol extraction support
 - bandit - Python security linter

strix/config/settings.py

@@ -164,7 +164,7 @@ class RuntimeSettings(BaseSettings):
     model_config = _BASE_CONFIG
 
     image: str = Field(
-        default="ghcr.io/usestrix/strix-sandbox:1.3.1",
+        default="ghcr.io/usestrix/strix-sandbox:1.4.0",
         alias="STRIX_IMAGE",
     )
     backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")

strix/report/dedupe.py

@@ -300,7 +300,15 @@ def _parse_dedupe_response(content: str) -> dict[str, Any]:
         raise ValueError(f"No JSON object found in dedupe response: {content[:500]}")
     parsed = json.loads(text[start : end + 1])
 
-    duplicate_id = str(parsed.get("duplicate_id") or "")[:64]
+    is_duplicate = parsed.get("is_duplicate")
+    if not isinstance(is_duplicate, bool):
+        raise TypeError("is_duplicate must be a boolean")
+    duplicate_id = parsed.get("duplicate_id") or ""
+    if is_duplicate and (not isinstance(duplicate_id, str) or not duplicate_id):
+        raise ValueError("A duplicate decision must name an existing report ID")
+    # Keep the ID verbatim: truncating or stripping it could turn an unknown ID
+    # into a different, existing one before the membership check below.
+    duplicate_id = str(duplicate_id)
     reason = str(parsed.get("reason") or "")[:500]
     try:
         confidence = float(parsed.get("confidence", 0.0))
@@ -308,13 +316,22 @@ def _parse_dedupe_response(content: str) -> dict[str, Any]:
         confidence = 0.0
 
     return {
-        "is_duplicate": bool(parsed.get("is_duplicate", False)),
+        "is_duplicate": is_duplicate,
         "duplicate_id": duplicate_id,
         "confidence": confidence,
         "reason": reason,
     }
 
 
+def _validate_duplicate_reference(
+    result: dict[str, Any], existing_reports: list[dict[str, Any]]
+) -> None:
+    if result["is_duplicate"] and not any(
+        report.get("id") == result["duplicate_id"] for report in existing_reports
+    ):
+        raise ValueError("Duplicate decision refers to an unknown report ID")
+
+
 def _extract_text(response: ModelResponse) -> str:
     parts: list[str] = []
     for item in response.output:
@@ -397,6 +414,7 @@ async def check_duplicate(
             }
 
         result = _parse_dedupe_response(content)
+        _validate_duplicate_reference(result, existing_reports)
 
         logger.info(
             "Deduplication check: is_duplicate=%s, confidence=%.2f, reason=%s",

strix/skills/README.md

@@ -40,7 +40,7 @@ The skills are dynamically injected into the agent's system prompt, allowing it
 
 Notable source-aware skills:
 - `source_aware_whitebox` (coordination): white-box orchestration playbook
-- `source_aware_sast` (custom): semgrep/AST/secrets/supply-chain static triage workflow
+- `source_aware_sast` (custom): opengrep/AST/secrets/supply-chain static triage workflow
 - `dependency_cve_scanning` (custom): trivy-based SCA workflow for reporting known dependency CVEs via `create_dependency_report`
 - `npx_confusion` (custom): npx/npm exec/bunx fallback and adjacent package-runner identity confusion, with runner-specific registry and reporting gates
 - `semantic_confusion` (vulnerabilities): cross-boundary parser, normalization, and representation mismatch analysis

strix/skills/coordination/source_aware_whitebox.md

@@ -14,22 +14,22 @@ Increase white-box coverage by combining source-aware triage with dynamic valida
 ## Recommended Workflow
 
 1. Build a quick source map before deep exploitation, including at least one AST-structural pass (`sg` or `tree-sitter`) scoped to relevant paths.
-   - For `sg` baseline, derive `sg-targets.txt` from `semgrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`) and run `xargs ... sg run` on that list.
-   - Only fall back to path heuristics when semgrep scope is unavailable.
+   - For `sg` baseline, derive `sg-targets.txt` from `opengrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`) and run `xargs ... sg run` on that list.
+   - Only fall back to path heuristics when opengrep scope is unavailable.
 2. Run first-pass static triage to rank high-risk paths.
 3. Use triage outputs to prioritize dynamic PoC validation.
 4. Keep findings evidence-driven: no report without validation.
 
 ## Source-Aware Triage Stack
 
-- `semgrep`: fast security-first triage and custom pattern scans
+- `opengrep`: fast security-first triage and custom pattern scans
 - `ast-grep` (`sg`): structural pattern hunting and targeted repo mapping
 - `tree-sitter`: syntax-aware parsing support for symbol and route extraction
 - `gitleaks` + `trufflehog`: complementary secret detection (working tree and history coverage)
 - `trivy fs`: dependency, misconfiguration, license, and secret checks
 
 Coverage target per repository:
-- one `semgrep` pass
+- one `opengrep` pass
 - one AST structural pass (`sg` and/or `tree-sitter`)
 - one secrets pass (`gitleaks` and/or `trufflehog`)
 - one `trivy fs` pass

strix/skills/custom/dependency_cve_scanning.md

@@ -136,8 +136,12 @@ fi
 - A finding with a call stack ⇒ `reachability=reachable_call_path`, put the
   call-path excerpt (entrypoint → vulnerable function) in
   `reachability_evidence`.
-- Listed as affecting a required module but with no reachable symbol ⇒ fall
-  back to the import/symbol checks below (`imported` / `not_imported`).
+- Listed as affecting a required module but with no reachable symbol ⇒ the
+  call graph found no path to the vulnerable function: `not_reached` when
+  application code imports the module (cite the govulncheck result and the
+  import), `not_imported` when nothing imports it. When govulncheck could not
+  analyze the module (build errors, missing deps), fall back to the
+  import/symbol checks below instead of claiming a level.
 
 **All other ecosystems — import check, then symbol match:**
 
@@ -148,15 +152,25 @@ fi
    `PyYAML` → `yaml`). No hits ⇒ `not_imported`, with the search scope stated
    in `reachability_evidence`. For a **transitive** dependency, the check is
    whether application code imports it directly; if not, it is reachable only
-   through the direct dependency — check whether the direct dep's usage can
-   hit it (if unclear, use `imported` when the direct dep is used at all).
+   through the packages that depend on it — walk every introducing chain
+   from the lockfile (e.g. `express > body-parser > qs`) and inspect the code
+   of the package one hop above the vulnerable one on each chain
+   (`body-parser`, not just `express`; its installed sources, or the class
+   references of its jar) for the affected API. No chain references it ⇒
+   `not_reached` (below), citing every artifact you inspected; referenced ⇒
+   that package's call is the usage site, continue the trace upward from
+   there. If you could not inspect every chain, or one of them is unclear,
+   the package is still loaded, so the level is `imported`, never
+   `not_reached`.
 2. **Symbol match — per CVE, not per package.** Read each CVE's own advisory
    (GHSA/NVD/OSV `affected[].ecosystem_specific.imports` or the advisory
    text) for the affected functions/classes/APIs. Search application code for
    those symbols (`ast-grep` pattern or `rg -n`). Hits ⇒
    `vulnerable_symbol_used`, with repo-relative `file:line` of each hit (up
-   to a handful) in `reachability_evidence`. Imported but no affected-symbol
-   usage found (or the advisory names no symbols) ⇒ `imported`.
+   to a handful) in `reachability_evidence`. Imported, search completed, and
+   you can say why the vulnerable code does not run here ⇒ `not_reached`
+   (below). Imported but the search was partial, the result is unclear, or
+   the advisory names no symbols ⇒ `imported`.
    Different CVEs on the same package usually affect **different** symbols
    (one hits a parser, another a header check) — never copy one CVE's
    verdict/evidence onto its siblings; run the symbol search against each
@@ -182,6 +196,23 @@ fi
    dynamic loading, unparsable sources) ⇒ `unknown` and say why in
    `assumptions`.
 
+**`not_reached` — loaded, but this CVE's vulnerable code does not run here.**
+Use it when the package is imported (so `not_imported` is wrong) and you
+showed that the code path the advisory describes cannot execute in this
+codebase, and `reachability_evidence` says what you checked. The judgement is
+per CVE: it rests on what triggers *this* flaw (an affected function, a mode,
+an option, a kind of input) against what this code does. Situations that
+commonly support it, as inspiration rather than a checklist: the affected API
+has no caller in application code and the search was complete; the only call
+site is behind a condition that is false here (a polyfill for an older
+runtime, a flag that is off, a path only a dev tool runs); a transitive
+package's parent never references the affected API; the package is build or
+test tooling that the shipped artifact never executes; a library compiled into
+the runtime whose flaw sits in a mode the application never uses (a TLS server
+path in a client-only service). An inconclusive or skipped check stays
+`imported`. `not_reached` is still an evidence level, not proof of safety:
+dynamic dispatch, reflection and framework wiring can evade static search.
+
 Cheap-first budgeting: the import check is one search per package — always do
 it. Do the per-CVE symbol match for every CVE whose advisory names affected
 symbols (they can be batched into one multi-pattern search per package);
@@ -189,13 +220,18 @@ prioritize `critical`/`high`/KEV when the budget is tight; a CVE whose symbol
 search was skipped may still be reported as `imported` (the import check is
 real evidence), but its `reachability_evidence` must state that the
 affected-symbol check was not performed, so a skipped search is never
-mistaken for a completed one with no hits. Never let this analysis stall
+mistaken for a completed one with no hits, and is never filed as
+`not_reached`. Never let this analysis stall
 reporting — `unknown` with a reason beats an unverified claim.
 
 Anti-overclaim rules:
 
 - `not_imported` still does NOT mean safe (dynamic `import()`/reflection/
   framework wiring evade static search) — never phrase it as "not exploitable".
+- `not_reached` needs the check that shows the vulnerable code does not run,
+  named in `reachability_evidence`; "no call found" after a partial search is
+  `imported`, and one CVE's `not_reached` never carries over to a sibling CVE
+  on the same package.
 - `reachable_call_path` is reserved for call-graph tools (govulncheck); a
   symbol grep hit is `vulnerable_symbol_used`, no matter how convinced you are.
 - The tool rejects any level other than `unknown` without

strix/skills/custom/source_aware_sast.md

@@ -1,6 +1,6 @@
 ---
 name: source-aware-sast
-description: Practical source-aware SAST and AST playbook for semgrep, ast-grep, gitleaks, and trivy fs
+description: Practical source-aware SAST and AST playbook for opengrep, ast-grep, gitleaks, and trivy fs
 ---
 
 # Source-Aware SAST Playbook
@@ -23,19 +23,19 @@ Run this baseline once per repository before deep narrowing:
 ART=/workspace/.source-aware
 mkdir -p "$ART"
 
-semgrep scan --config p/default --config p/golang --config p/secrets \
-  --metrics=off --json --output "$ART/semgrep.json" .
-# Build deterministic AST targets from semgrep scope (no hardcoded path guessing)
+opengrep scan --config /opt/opengrep-rules --taint-intrafile \
+  --json --output "$ART/opengrep.json" .
+# Build deterministic AST targets from opengrep scope (no hardcoded path guessing)
 python3 - <<'PY'
 import json
 from pathlib import Path
 
 art = Path("/workspace/.source-aware")
-semgrep_json = art / "semgrep.json"
+opengrep_json = art / "opengrep.json"
 targets_file = art / "sg-targets.txt"
 
 try:
-    data = json.loads(semgrep_json.read_text(encoding="utf-8"))
+    data = json.loads(opengrep_json.read_text(encoding="utf-8"))
 except Exception:
     targets_file.write_text("", encoding="utf-8")
     raise
@@ -63,17 +63,18 @@ trivy fs --scanners vuln,misconfig --timeout 30m --offline-scan \
   --format json --output "$ART/trivy-fs.json" . || true
 ```
 
-## Semgrep First Pass
+## Opengrep First Pass
 
-Use Semgrep as the default static triage pass:
+Use Opengrep as the default static triage pass. Rules are bundled offline in `/opt/opengrep-rules` (one directory per language, plus `generic/secrets`):
 
 ```bash
-# Preferred deterministic profile set (works with --metrics=off)
-semgrep scan --config p/default --config p/golang --config p/secrets \
-  --metrics=off --json --output /workspace/.source-aware/semgrep.json .
+# Full bundled ruleset
+opengrep scan --config /opt/opengrep-rules --taint-intrafile \
+  --json --output /workspace/.source-aware/opengrep.json .
 
-# If you choose auto config, do not combine it with --metrics=off
-semgrep scan --config auto --json --output /workspace/.source-aware/semgrep-auto.json .
+# Narrow to the target stack when the full set is slow or noisy
+opengrep scan --config /opt/opengrep-rules/python --config /opt/opengrep-rules/generic/secrets \
+  --taint-intrafile --json --output /workspace/.source-aware/opengrep-python.json .
 ```
 
 If diff scope is active, restrict to changed files first, then expand only when needed.

strix/skills/frameworks/django.md

@@ -205,10 +205,10 @@ Jinja2 backend without autoescape: `{{7*7}}`, RCE gadgets if sandbox misconfigur
 
 ## Tooling
 
-Static analysis is the fastest way to reach the sinks above in white-box scope. The sandbox ships `python`/`pipx`, `semgrep`, `bandit`, `ast-grep`, and `ripgrep`.
+Static analysis is the fastest way to reach the sinks above in white-box scope. The sandbox ships `python`/`pipx`, `opengrep`, `bandit`, `ast-grep`, and `ripgrep`.
 
 - **bandit** (preinstalled) — Python security linter; flags `mark_safe`, `extra()`, `RawSQL`, `subprocess`, weak crypto, hardcoded secrets: `bandit -r . -ll`
-- **semgrep** (preinstalled) with the Django ruleset — higher-signal than bandit for framework-specific bugs (`.extra()`, `RawSQL`, `|safe`, `csrf_exempt`, `ALLOWED_HOSTS=['*']`): `semgrep --config p/django .`
+- **opengrep** (preinstalled) with the bundled Django rules — higher-signal than bandit for framework-specific bugs (`.extra()`, `RawSQL`, `|safe`, `csrf_exempt`, `ALLOWED_HOSTS=['*']`): `opengrep scan --config /opt/opengrep-rules/python/django .`
 - **pip-audit** (PyPA) — dependency CVE scanner for known-vuln Django/DRF/simplejwt versions: `pipx install pip-audit && pip-audit -r requirements.txt`
 - **ast-grep** (preinstalled) — quick structural grep for risky calls without a full SAST run: `ast-grep run -p 'mark_safe($X)' -l python`
 

strix/skills/scan_modes/deep.md

@@ -15,7 +15,7 @@ Thorough understanding before exploitation. Test every parameter, every endpoint
 
 **Whitebox (source available)**
 - Map every file, module, and code path in the repository
-- Start with broad source-aware triage (`semgrep`, `ast-grep`, `gitleaks`, `trufflehog`, `trivy fs`) and use outputs to drive deep review
+- Start with broad source-aware triage (`opengrep`, `ast-grep`, `gitleaks`, `trufflehog`, `trivy fs`) and use outputs to drive deep review
 - Execute at least one structural AST pass (`sg` and/or Tree-sitter) per repository and store artifacts for reuse
 - Keep AST artifacts bounded and query-driven (target relevant paths/sinks first; avoid whole-repo generic function dumps)
 - Use syntax-aware parsing (Tree-sitter tooling) to improve symbol, route, and sink extraction quality

strix/skills/scan_modes/quick.md

@@ -15,7 +15,7 @@ Optimize for fast feedback on critical security issues. Skip exhaustive enumerat
 
 **Whitebox (source available)**
 - Focus on recent changes: git diffs, new commits, modified files—these are most likely to contain fresh bugs
-- Run a fast static triage on changed files first (`semgrep`, then targeted `sg` queries)
+- Run a fast static triage on changed files first (`opengrep`, then targeted `sg` queries)
 - Run at least one lightweight AST pass (`sg` or Tree-sitter) so structural mapping is not skipped
 - Keep AST commands tightly scoped to changed or high-risk paths; avoid broad repository-wide pattern dumps
 - Run quick secret and dependency checks (`gitleaks`, `trufflehog`, `trivy fs`) scoped to changed areas when possible

strix/skills/scan_modes/standard.md

@@ -15,7 +15,7 @@ Systematic testing across the full attack surface. Understand the application be
 
 **Whitebox (source available)**
 - Map codebase structure: modules, entry points, routing
-- Run `semgrep` first-pass triage to prioritize risky flows before deep manual review
+- Run `opengrep` first-pass triage to prioritize risky flows before deep manual review
 - Run at least one AST-structural mapping pass (`sg` and/or Tree-sitter), then use outputs for route, sink, and trust-boundary mapping
 - Keep AST output bounded to relevant paths and hypotheses; avoid whole-repo generic function dumps
 - Identify architecture pattern (MVC, microservices, monolith)

strix/skills/tooling/opengrep.md

@@ -0,0 +1,69 @@
+---
+name: opengrep
+description: Exact Opengrep CLI structure, bundled offline rules, scoped rule selection, taint mode, and automation-safe output patterns.
+---
+
+# Opengrep CLI Playbook
+
+Official docs:
+- https://github.com/opengrep/opengrep
+- https://github.com/opengrep/opengrep-rules
+
+Canonical syntax:
+`opengrep scan [flags] [targets]`
+
+Bundled rules:
+- `/opt/opengrep-rules` holds the full ruleset, one directory per language (`python`, `javascript`, `typescript`, `go`, `java`, `php`, `ruby`, …) plus `generic/secrets`, `dockerfile`, `terraform`, `yaml`, and `strix` (Strix-authored rules, e.g. GitHub-owned actions not pinned to a commit SHA)
+- Framework rules sit under the language (`python/django`, `python/flask`, `javascript/express`, …)
+
+High-signal flags:
+- `--config <path>` rule file or directory; repeat for several
+- `--taint-intrafile` intra-file inter-procedural taint (follows data across functions in one file)
+- `--json` / `--sarif` output format
+- `--output <file>` write findings to file
+- `--severity <level>` filter by severity (`INFO`, `WARNING`, `ERROR`)
+- `--error` return non-zero exit when findings exist
+- `--quiet` suppress progress noise
+- `--jobs <n>` parallel workers
+- `--timeout <seconds>` per-rule, per-file timeout
+- `--exclude <pattern>` / `--include <pattern>` path filters
+- `--exclude-rule <rule_id>` suppress specific rule
+- `--baseline-commit <sha>` only report findings introduced after baseline
+
+Agent-safe baseline for automation:
+`opengrep scan --config /opt/opengrep-rules --taint-intrafile --json --output opengrep.json --quiet --jobs 4 --timeout 20 /workspace`
+
+Common patterns:
+- Full bundled scan:
+  `opengrep scan --config /opt/opengrep-rules --json --output opengrep.json --quiet /workspace`
+- High-severity focused pass:
+  `opengrep scan --config /opt/opengrep-rules --severity ERROR --json --output opengrep_high.json --quiet /workspace`
+- SARIF output:
+  `opengrep scan --config /opt/opengrep-rules --sarif --output opengrep.sarif --quiet /workspace`
+- Language- or framework-specific rules:
+  `opengrep scan --config /opt/opengrep-rules/python --config /opt/opengrep-rules/generic/secrets --json --output opengrep_python.json --quiet /workspace`
+- Scoped directory scan:
+  `opengrep scan --config /opt/opengrep-rules --json --output opengrep_api.json --quiet /workspace/services/api`
+- Custom rule:
+  `opengrep scan --config ./rules/my-rule.yaml --json --output opengrep_custom.json --quiet /workspace`
+
+Critical correctness rules:
+- Always provide an explicit `--config` from `/opt/opengrep-rules` or a local rule file. Registry shorthands (`p/...`, `auto`) fetch rules from the network; do not use them.
+- Opengrep has no telemetry; there is no `--metrics` flag, and passing one fails the scan.
+- Prefer `--json --output <file>` or `--sarif --output <file>` for machine-readable downstream processing. JSON keeps `paths.scanned` and `results[].path`.
+- Keep the target path explicit; use an absolute or clearly scoped workspace path instead of `.` when possible.
+
+Usage rules:
+- Start with the full `/opt/opengrep-rules` set unless the task clearly calls for a narrower language or framework directory.
+- Add `--taint-intrafile` for injection-class hunting (SQLi, command injection, SSRF, path traversal) in supported languages.
+- Use `--quiet` in automation to reduce noisy logs.
+- Use `--jobs` and `--timeout` explicitly for reproducible runtime behavior.
+- `PartialParsing` errors on templates are normal; they do not invalidate the run.
+
+Failure recovery:
+- If scans are too slow, narrow the target path and the rule directories before changing engine settings.
+- If scans time out, increase `--timeout` modestly or lower `--jobs`.
+- If output is too broad, scope `--config`, add `--severity`, or exclude known irrelevant paths.
+
+If uncertain, query web_search with:
+`site:github.com/opengrep/opengrep <flag>`

strix/skills/tooling/semgrep.md

@@ -1,72 +0,0 @@
----
-name: semgrep
-description: Exact Semgrep CLI structure, metrics-off scanning, scoped ruleset selection, and automation-safe output patterns.
----
-
-# Semgrep CLI Playbook
-
-Official docs:
-- https://semgrep.dev/docs/cli-reference
-- https://semgrep.dev/docs/getting-started/cli
-- https://semgrep.dev/docs/semgrep-code/semgrep-pro-engine-intro
-
-Canonical syntax:
-`semgrep scan [flags]`
-
-High-signal flags:
-- `--config <rule_or_ruleset>` ruleset, registry pack, local rule file, or directory
-- `--metrics=off` disable telemetry and metrics reporting
-- `--json` JSON output
-- `--sarif` SARIF output
-- `--output <file>` write findings to file
-- `--severity <level>` filter by severity
-- `--error` return non-zero exit when findings exist
-- `--quiet` suppress progress noise
-- `--jobs <n>` parallel workers
-- `--timeout <seconds>` per-file timeout
-- `--exclude <pattern>` exclude path pattern
-- `--include <pattern>` include path pattern
-- `--exclude-rule <rule_id>` suppress specific rule
-- `--baseline-commit <sha>` only report findings introduced after baseline
-- `--pro` enable Pro engine if available
-- `--oss-only` force OSS engine only
-
-Agent-safe baseline for automation:
-`semgrep scan --config p/default --metrics=off --json --output semgrep.json --quiet --jobs 4 --timeout 20 /workspace`
-
-Common patterns:
-- Default security scan:
-  `semgrep scan --config p/default --metrics=off --json --output semgrep.json --quiet /workspace`
-- High-severity focused pass:
-  `semgrep scan --config p/default --severity ERROR --metrics=off --json --output semgrep_high.json --quiet /workspace`
-- OWASP-oriented scan:
-  `semgrep scan --config p/owasp-top-ten --metrics=off --sarif --output semgrep.sarif --quiet /workspace`
-- Language- or framework-specific rules:
-  `semgrep scan --config p/python --config p/secrets --metrics=off --json --output semgrep_python.json --quiet /workspace`
-- Scoped directory scan:
-  `semgrep scan --config p/default --metrics=off --json --output semgrep_api.json --quiet /workspace/services/api`
-- Pro engine check or run:
-  `semgrep scan --config p/default --pro --metrics=off --json --output semgrep_pro.json --quiet /workspace`
-
-Critical correctness rules:
-- Always include `--metrics=off`; Semgrep sends telemetry by default.
-- Always provide an explicit `--config`; do not rely on vague or implied defaults.
-- Prefer `--json --output <file>` or `--sarif --output <file>` for machine-readable downstream processing.
-- Keep the target path explicit; use an absolute or clearly scoped workspace path instead of `.` when possible.
-- If Pro availability matters, check it explicitly with a bounded command before assuming cross-file analysis exists.
-
-Usage rules:
-- Start with `p/default` unless the task clearly calls for a narrower pack.
-- Add focused packs such as `p/secrets`, `p/python`, or `p/javascript` only when they match the target stack.
-- Use `--quiet` in automation to reduce noisy logs.
-- Use `--jobs` and `--timeout` explicitly for reproducible runtime behavior.
-- Do not use `-h`/`--help` for routine operation unless absolutely necessary.
-
-Failure recovery:
-- If scans are too slow, narrow the target path and reduce the active rulesets before changing engine settings.
-- If scans time out, increase `--timeout` modestly or lower `--jobs`.
-- If output is too broad, scope `--config`, add `--severity`, or exclude known irrelevant paths.
-- If Pro mode fails, rerun with `--oss-only` or without `--pro` and note the loss of cross-file coverage.
-
-If uncertain, query web_search with:
-`site:semgrep.dev semgrep <flag> cli`

strix/tools/reporting/tool.py

@@ -1693,6 +1693,7 @@ _VALID_REACHABILITY = frozenset(
     {
         "not_imported",
         "imported",
+        "not_reached",
         "vulnerable_symbol_used",
         "reachable_call_path",
         "unknown",
@@ -1840,6 +1841,9 @@ def _build_dependency_metadata(
 _REACHABILITY_EVIDENCE_LABELS = {
     "not_imported": "not imported by application code",
     "imported": "imported by application code; affected API usage unconfirmed",
+    "not_reached": (
+        "imported by application code; the vulnerable code of this advisory is not reached"
+    ),
     "vulnerable_symbol_used": "the advisory's affected API is used in application code",
     "reachable_call_path": (
         "a call path from application code to the vulnerable function was proven"
@@ -2157,6 +2161,11 @@ async def create_dependency_report(
       can evade static search).
     - ``imported`` — application code imports the package, but usage of
       the advisory's affected API was not confirmed.
+    - ``not_reached`` — application code imports the package, and the
+      analysis showed that the vulnerable code of this advisory does not
+      run here (the affected API has no caller, the only call site is
+      behind a condition that is false in this codebase, the parent
+      package never reaches it, ...). Per advisory, never per package.
     - ``vulnerable_symbol_used`` — the advisory's affected
       function/class/API appears in application code.
     - ``reachable_call_path`` — a call-graph tool (e.g. ``govulncheck``)
@@ -2210,8 +2219,9 @@ async def create_dependency_report(
             repository root. This binds the finding to its exact file so
             remediation can target the right repository.
         reachability: Usage-evidence level from static analysis — one of
-            ``not_imported`` / ``imported`` / ``vulnerable_symbol_used`` /
-            ``reachable_call_path`` / ``unknown``. Claim only what the
+            ``not_imported`` / ``imported`` / ``not_reached`` /
+            ``vulnerable_symbol_used`` / ``reachable_call_path`` /
+            ``unknown``. Claim only what the
             evidence proves; when in doubt use ``unknown``.
         reachability_evidence: **Required.** The concrete proof for the
             claimed level, or, for ``unknown``, what you searched and why

tests/test_dedupe_decisions.py

@@ -0,0 +1,159 @@
+"""Only validated model decisions may suppress a finding."""
+
+from __future__ import annotations
+
+import json
+from typing import TYPE_CHECKING, Any
+from unittest.mock import AsyncMock
+
+import pytest
+from agents.items import ModelResponse
+from agents.usage import Usage
+from openai.types.responses import ResponseOutputMessage, ResponseOutputText
+
+from strix.config import loader
+from strix.report import dedupe
+from strix.report.state import ReportState, get_global_report_state, set_global_report_state
+from strix.tools.reporting.tool import _do_create
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from pathlib import Path
+
+
+@pytest.fixture
+def report_state(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Iterator[ReportState]:
+    monkeypatch.chdir(tmp_path)
+    previous = get_global_report_state()
+    state = ReportState(run_name="dedupe-decisions")
+    set_global_report_state(state)
+    state.add_vulnerability_report(title="Existing finding", severity="low")
+    try:
+        yield state
+    finally:
+        set_global_report_state(previous)
+
+
+def _mock_judge(monkeypatch: pytest.MonkeyPatch, decision: dict[str, Any]) -> AsyncMock:
+    settings = loader.load_settings().model_copy(deep=True)
+    settings.llm.model = "openai/synthetic-model"
+    model = AsyncMock()
+    model.get_response.return_value = ModelResponse(
+        output=[
+            ResponseOutputMessage(
+                id="msg_synthetic",
+                type="message",
+                role="assistant",
+                status="completed",
+                content=[
+                    ResponseOutputText(
+                        type="output_text",
+                        annotations=[],
+                        text=json.dumps({"confidence": 0.95, "reason": "Synthetic", **decision}),
+                    )
+                ],
+            )
+        ],
+        usage=Usage(),
+        response_id="synthetic",
+    )
+    monkeypatch.setattr(dedupe, "load_settings", lambda: settings)
+    monkeypatch.setattr(dedupe, "configure_sdk_model_defaults", lambda _: None)
+    monkeypatch.setattr(dedupe, "resolve_dedupe_model", lambda *_: model)
+    return model
+
+
+async def _file_finding() -> dict[str, Any]:
+    return await _do_create(
+        title="New finding",
+        description="The endpoint reflects unencoded input.",
+        impact="The reflected script executes in a victim's browser.",
+        target="https://example.invalid",
+        technical_analysis="Input is interpolated into HTML without encoding.",
+        poc_description="Open the endpoint with the reflected parameter.",
+        poc_script_code="print('synthetic reproduction')",
+        remediation_steps="Encode output for its HTML context.",
+        evidence="The synthetic response contains the unencoded parameter.",
+        assumptions="A victim follows the crafted link.",
+        counterevidence="No encoding or content security policy is present.",
+        confidence="high",
+        severity_change_conditions="A strict content security policy would lower the impact.",
+        fix_effort="low",
+        cvss_breakdown={
+            "attack_vector": "N",
+            "attack_complexity": "L",
+            "privileges_required": "N",
+            "user_interaction": "R",
+            "scope": "U",
+            "confidentiality": "L",
+            "integrity": "L",
+            "availability": "N",
+        },
+        endpoint="/search",
+        method="GET",
+        cve=None,
+        cwe="CWE-79",
+        code_locations=None,
+    )
+
+
+@pytest.mark.parametrize("value", ["false", "true", 0, 1, None, [], {}])
+def test_dedupe_parser_requires_a_boolean(value: Any) -> None:
+    with pytest.raises(TypeError, match="is_duplicate"):
+        dedupe._parse_dedupe_response(json.dumps({"is_duplicate": value}))
+
+
+@pytest.mark.parametrize(
+    "decision",
+    [
+        {"is_duplicate": "false", "duplicate_id": "vuln-0001"},
+        {"is_duplicate": "true", "duplicate_id": "vuln-0001"},
+        {"is_duplicate": 1, "duplicate_id": "vuln-0001"},
+        {"is_duplicate": True, "duplicate_id": "vuln-9999"},
+        {"is_duplicate": True, "duplicate_id": ""},
+        {"is_duplicate": True, "duplicate_id": None},
+        {"is_duplicate": True, "duplicate_id": ["vuln-0001"]},
+        {"is_duplicate": True},
+    ],
+)
+async def test_invalid_dedupe_decision_does_not_suppress_finding(
+    report_state: ReportState, monkeypatch: pytest.MonkeyPatch, decision: dict[str, Any]
+) -> None:
+    model = _mock_judge(monkeypatch, decision)
+
+    result = await _file_finding()
+
+    assert result["success"] is True
+    model.get_response.assert_awaited_once()
+    saved = json.loads((report_state.get_run_dir() / "vulnerabilities.json").read_text())
+    assert [report["title"] for report in saved] == ["Existing finding", "New finding"]
+    assert (report_state.get_run_dir() / "vulnerabilities" / "vuln-0002.md").is_file()
+
+
+@pytest.mark.parametrize("is_duplicate", [False, True])
+async def test_valid_dedupe_decisions_keep_their_meaning(
+    report_state: ReportState, monkeypatch: pytest.MonkeyPatch, is_duplicate: bool
+) -> None:
+    # An extraneous ID must not turn a valid false decision into a duplicate.
+    _mock_judge(monkeypatch, {"is_duplicate": is_duplicate, "duplicate_id": "vuln-0001"})
+
+    result = await _file_finding()
+
+    assert result["success"] is not is_duplicate
+    saved = json.loads((report_state.get_run_dir() / "vulnerabilities.json").read_text())
+    assert len(saved) == (1 if is_duplicate else 2)
+    if is_duplicate:
+        assert result["duplicate_of"] == "vuln-0001"
+
+
+async def test_dedupe_id_is_matched_without_truncation(monkeypatch: pytest.MonkeyPatch) -> None:
+    existing_id = "x" * 64
+    _mock_judge(monkeypatch, {"is_duplicate": True, "duplicate_id": existing_id + "-unknown"})
+
+    result = await dedupe.check_duplicate(
+        {"title": "New finding"}, [{"id": existing_id, "title": "Existing finding"}]
+    )
+
+    assert result["is_duplicate"] is False
+    assert "error" in result

tests/test_reporting_fields.py

@@ -668,6 +668,39 @@ async def test_dependency_report_records_reachability(report_state: ReportState)
     assert report["severity"] == "high"
 
 
+async def test_dependency_report_records_not_reached(report_state: ReportState) -> None:
+    result = await _do_create_dependency(
+        title="CVE-2021-23337 in lodash 4.17.20",
+        description="Command injection via template.",
+        target="repo/package.json",
+        cve="CVE-2021-23337",
+        package_name="lodash",
+        installed_version="4.17.20",
+        impact="Command injection where template is used.",
+        remediation_steps="Upgrade to 4.17.21.",
+        assumptions="Static search only; no dynamic dispatch into lodash was found.",
+        package_ecosystem="npm",
+        manifest_path="package-lock.json",
+        fixed_version="4.17.21",
+        cwe=None,
+        advisory_cvss=7.2,
+        technical_analysis=None,
+        fix_effort="low",
+        reachability="not_reached",
+        reachability_evidence=(
+            "src/util/strings.ts:3 imports lodash; a complete search of src/ finds no "
+            "call to _.template, the only API the advisory affects."
+        ),
+        contextual_cvss_breakdown=_DEP_CONTEXT,
+        contextual_cvss_reasoning=_DEP_REASONING,
+    )
+
+    assert result["success"] is True
+    report = report_state.vulnerability_reports[0]
+    assert report["dependency_metadata"]["reachability"] == "not_reached"
+    assert "the vulnerable code of this advisory is not reached" in report["evidence"]
+
+
 async def test_dependency_report_rejects_reachability_without_evidence(
     report_state: ReportState,
 ) -> None: