QG323 Write outside its own words¶
| Type | Security hotspot |
| Severity | none: a review item |
| Front end | a synthesised host and its router |
| Guardrail category (Vassilev 2026) | B. Policy & Governance Guardrails |
| AI RMF functions (NIST AI 100-1) | MAP, MEASURE |
| Why these functions | the catalogue's assignment, not the article's chain (GOVERN, MAP, MANAGE): the measurement maps which words reach a write; whether they should is the team's decision, so the finding itself governs and manages nothing |
| OWASP | ASI02:2026 Tool Misuse and Exploitation |
| Gates by default | no, unless the project's quality profile adds it |
Raised when¶
A write resolved with no question where none of the wording's content words is one of the write's own declared terms.
Why it matters¶
The selector reads synonyms on purpose, so this is a review item: it shows what a user can say to reach the write, with the rewrite chain that got there.
How to fix it¶
Nothing is required. A team that wants the write narrower removes the row or rung named in the chain.
What the finding carries¶
A location in the document the team edits, a fingerprint that survives unrelated edits, a reproduction (a transcript replayed against NeMo Guardrails for a policy, a dialogue case played through the selector for a router, or the gate's inputs reproduced by agreement), and, where the scan can produce one, a fix whose re-scan it has already run. See the catalogue for the other rules.