What the reviewer found
A security-auditor skill's reference table of attack indicators (prompt-injection phrases, `requests.post('https://evil.com/...')`, `sudo`/`chmod 777`, `pickle.loads`) to flag when auditing someone else's code — none of it is code this skill itself runs.
dual-use— a security tool that can be misused
What was read
The file as it ships in adriannoes/awesome-agentic-ai:
cursor-claude-codex/skills/alirezarezvani-skills/skill-security-auditor/SKILL.md
What the static scan said
The scan flagged 9things. The reviewer kept 0 and dismissed 9 as false.
P1Instruction-override phrasing — false positiveAR3Nullifies safety policies — false positiveE1Sends data to an external URL — false positivePE2Asks for root — false positivePE3Reaches for credential files — false positiveSC3Encoded or obfuscated payload — false positiveEA1Unrestricted tool access — 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.