QG102 Write reached by a slip

Type	Security hotspot
Severity	none: a review item
Front end	a synthesised host and its router
Guardrail category (Vassilev 2026)	E. Action & Execution Guardrails
AI RMF functions (NIST AI 100-1)	MAP
Why these functions	the catalogue's assignment, not the article's chain (GOVERN, MANAGE): a hotspot asks a person to map whether a write reached by a slip is intended; nothing is governed or managed until they decide
OWASP	ASI02:2026 Tool Misuse and Exploitation, ASI09:2026 Human-Agent Trust Exploitation
Gates by default	no, unless the project's quality profile adds it

Raised when

A write a misspelling alone reaches on some agent.

Why it matters

The selector puts such a write to the user before calling it. The host has to honour that question; a host that calls through it runs a write on a word nobody typed.

How to fix it

Make sure the host asks before calling a write the router marks for confirmation.

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.