From 46767e6eb5ad52cb48dbcef12db2f3dfeec08c26 Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Thu, 2 Jul 2026 22:36:47 +0200
Subject: [PATCH] Note the chaining exception on the LLM-output out-of-scope
 status

The short Status claims stated the risk is out of scope flatly. They now carry the same caveat the page body already spells out: it is out of scope on its own, but in scope when proven as part of a chain with a legitimate Open WebUI vulnerability per the Security Policy.
---
 docs/security/accepted-risks/index.mdx                       | 2 +-
 docs/security/accepted-risks/llm-output-unpredictability.mdx | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/security/accepted-risks/index.mdx b/docs/security/accepted-risks/index.mdx
index 64f1ff68..6343792a 100644
--- a/docs/security/accepted-risks/index.mdx
+++ b/docs/security/accepted-risks/index.mdx
@@ -44,5 +44,5 @@ A residual whose practical impact is dominated by network and scheduling noise,
 
 | Risk | Class | Mitigation | Status |
 | :--- | :--- | :--- | :--- |
-| [LLM output unpredictability](./llm-output-unpredictability) | Inherent model behavior (OWASP LLM Top 10) | System hardened around the model; model bound by caller's privileges | Inherent to LLMs; out of scope as a vulnerability |
+| [LLM output unpredictability](./llm-output-unpredictability) | Inherent model behavior (OWASP LLM Top 10) | System hardened around the model; model bound by caller's privileges | Inherent to LLMs; out of scope on its own, unless chained with a legitimate vulnerability (see [Security Policy](../security-policy)) |
 | [Authentication timing side-channel](./auth-timing) | CWE-208, Observable Timing Discrepancy | bcrypt cost equalised across all sign-in paths | Mitigated, residual accepted |
diff --git a/docs/security/accepted-risks/llm-output-unpredictability.mdx b/docs/security/accepted-risks/llm-output-unpredictability.mdx
index f2869e86..849f933e 100644
--- a/docs/security/accepted-risks/llm-output-unpredictability.mdx
+++ b/docs/security/accepted-risks/llm-output-unpredictability.mdx
@@ -7,7 +7,7 @@ title: "LLM Output Unpredictability"
 |  |  |
 | :--- | :--- |
 | **Class** | Inherent model behavior (prompt injection, jailbreaks, unsafe or hallucinated output) — OWASP LLM Top 10 |
-| **Status** | Inherent to LLMs; not a remediable application defect; out of scope as a vulnerability |
+| **Status** | Inherent to LLMs; not a remediable application defect; out of scope as a vulnerability on its own, unless proven as part of a chain with a legitimate Open WebUI vulnerability per the [Security Policy](../security-policy) |
 
 ---