What the reviewer found
A skill-auditor tool whose SKILL.md documents the injection phrases and network patterns it scans FOR, such as "ignore previous instructions" and fetch(url?key=...). None of these are executed or targeted at the reader; they are the detection checklist.
example-or-fixture— an example or test fixture
What was read
The file as it ships in UseAI-pro/openclaw-skills-security:
skills/skill-auditor/SKILL.md
What the static scan said
The scan flagged 5things. The reviewer kept 0 and dismissed 5 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveAR3Nullifies safety policies — false positiveNETMakes network calls — false positiveSHRuns shell commands — false positive
How this review was made
Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.