Files
rea/src/application/binaryDiagnostics/ElfNotesService.ts
T
4ef916da03 feat(pe): inspect import and delay-load tables (#6509)
* feat(pe): inspect import and delay-load tables

Add inspect_pe_imports / inspect-pe-imports to read PE32/PE32+ import
and delay-load directories without executing the image. The report keeps
DLL names, named and ordinal functions, ILT/IAT RVAs, and a pefile
import hash of the standard import table. A missing directory is
observed absence, not proof the image never imported APIs.

* fix(pe): default PE import fixture options

Allow peImportImage() without an argument so CLI and filesystem tests
can use the KERNEL32 sample without repeating an empty options object.

* test(pe): keep import path cases on the dedicated MCP contract

inspect_pe_imports already rejects relative MCP paths in its own
boundary test. Leave the shared absolute-path matrix to tools whose
handler issue projection matches that suite's expected shape.

* fix(native): index virtual-to-file mapping lookups

mappedFileOffset scans every mapping twice per span, so a parser that
translates one span per table entry costs sections x entries. Add
fileMappingLookup, which builds an O(n log n) interval index once and
answers each span in O(log n) with the same accept, reject and
translation results. A differential test checks it against
mappedFileOffset over randomized overlapping mappings and zero fills.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g

* fix(pe): report partial import evidence and exact pefile hashes

- Withhold imphash with an explicit reason whenever the standard import
  table is partial (unreadable names or thunks, missing tables), or when
  pefile 2024.8.26 would hash a different row sequence: invalid or
  truncated names, ordinal 0, descriptors without functions, tables its
  bounds or repeat/spread heuristics discard, and its 8192-thunk import
  symbol cap. Delay-load issues do not withhold it.
- Hash ordinal imports with pefile's complete ordlookup tables and its
  ord<decimal> fallback instead of declining unmapped ordinals.
- Report a nonterminal descriptor whose FirstThunk is zero, and a
  delay-load descriptor whose IAT or INT RVA is zero, as malformed_entry
  partial coverage instead of a complete empty inventory.
- Directory evidence lists the file spans actually consumed for the
  descriptor array and terminator; discontiguous mappings produce
  separate spans and separate Evidence ranges.
- Carry exhausted limits as PeImportLimitFailure.limit and derive
  recovery from it; the fixed 16 MiB retained-text ceiling reports a
  fixed allowance instead of max_file_bytes advice.
- Translate RVAs through the indexed mapping lookup and yield with a
  cancellation check every 1024 table entries.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g

* fix(pe): read only own ordinal tables for DLL names

DLL names such as constructor and __proto__ pass pefile's name rule but
resolved inherited object members, throwing before the ord<n> fallback.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g

* fix(native): preserve PE import facts and prove hash compatibility

* test(native): verify PE import workflows and measured costs

* refactor(native): narrow PE facts across the container union

* docs(native): record integrated PE import validation

* fix(native): bound every PE import RVA span

* docs(native): measure RVA guard completed workflows

* fix(pe): reconcile import coverage with retained rows

* fix(pe): retain partial imports at descriptor mapping gaps

---------

Co-authored-by: Matt Van Horn <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
Co-authored-by: gensokyo-dev <[email protected]>
2026-10-24 11:44:12 +08:00

130 lines
4.0 KiB
TypeScript

import { isAbsolute } from "node:path";
import type { ExecutionOptions } from "../AnalysisProvider.js";
import type { ElfNotesPort } from "./ElfNotesPort.js";
import type { AnalysisError } from "../../domain/analysisErrorBase.js";
import {
AnalysisCancelledError,
AnalysisInputError,
AnalysisOutputError,
} from "../../domain/analysisErrorCore.js";
import { createEvidence, type Evidence } from "../../domain/evidence.js";
import {
inspectElfNotesInputSchema,
elfNotesSchema,
type ElfNotes,
} from "../../domain/native/elfNotes.js";
import { analysisInputErrorFromIssues } from "../../domain/inputIssueProjection.js";
import { BINARY_ARCHITECTURES } from "../../domain/binaryTargetTypes.js";
import { elfArchitecture } from "../../domain/elfFixedHeader.js";
import { err, type Result } from "../../domain/result.js";
import { completeProviderEvidence } from "../ProviderOperationExecution.js";
const OPERATION = "inspect_elf_notes";
/** Shared caller validation, output parsing and Evidence provenance for CLI/MCP. */
export class ElfNotesService {
constructor(readonly provider: ElfNotesPort) {}
close(): Promise<void> {
return this.provider.close?.() ?? Promise.resolve();
}
async inspect(
rawInput: unknown,
options?: ExecutionOptions,
): Promise<Result<Evidence, AnalysisError>> {
if (options?.signal?.aborted)
return err(
new AnalysisCancelledError(OPERATION, { cause: options.signal.reason }),
);
const input = inspectElfNotesInputSchema.safeParse(rawInput);
if (!input.success)
return err(
analysisInputErrorFromIssues(OPERATION, input.error.issues, rawInput, {
cause: input.error,
}),
);
if (!isAbsolute(input.data.path))
return err(
new AnalysisInputError(OPERATION, undefined, [
{
path: ["path"],
reason: "invalid_format",
message: "Expected an absolute filesystem path on this host.",
},
]),
);
const result = await this.provider.inspect(input.data, options);
if (!result.ok) return result;
const report = elfNotesSchema.safeParse(result.value);
if (
!report.success ||
report.data.artifact.path !== input.data.path ||
!validReport(
report.data,
input.data.max_entries,
input.data.max_file_bytes,
)
)
return err(
new AnalysisOutputError(
OPERATION,
"ELF note provider returned malformed output or changed artifact identity.",
),
);
const value = report.data;
const architecture = BINARY_ARCHITECTURES.find(
(supported) => supported === elfArchitecture(value.machine),
);
const locations = [
{ kind: "artifact-path" as const, path: value.artifact.path },
...value.tables.map((table) => ({
kind: "file-offset-range" as const,
start: table.location.offset,
end: table.location.offset + table.location.bytes,
})),
];
return completeProviderEvidence(
createEvidence(
{
path: value.artifact.path,
format: "elf",
sha256: value.artifact.sha256,
...(architecture === undefined ? {} : { architecture }),
},
this.provider.identity,
{
operation: OPERATION,
parameters: input.data,
result: value,
confidence: "observed",
limitations: value.limitations,
locations,
},
),
options?.signal,
);
}
}
const validReport = (
report: ElfNotes,
maxEntries: number,
maxBytes: number,
): boolean => {
const inside = ({ offset, bytes }: { offset: number; bytes: number }) =>
offset <= report.artifact.bytes - bytes;
if (
report.artifact.bytes > maxBytes ||
report.coverage.examined_entries > maxEntries ||
report.entries.length > maxEntries
)
return false;
return (
report.tables.every((table) => inside(table.location)) &&
report.entries.every(
(entry) => inside(entry.location) && inside(entry.descriptor.location),
)
);
};