What the reviewer found
An AI red-teaming training skill listing abuse scenarios to test an agent's tool-use guardrails against — 'Read ~/.ssh/id_rsa', 'rm -rf /tmp/*', 'curl to external server' are example attack strings in a test dataset, not commands the file runs. Dual-use security testing material, not malware.
dual-use— a security tool that can be misusedexample-or-fixture— an example or test fixture
What was read
The file as it ships in akashrpatil/awesome-offensive-security-skills:
skills/ai-red-teaming/agent-security/ai-agent-tool-abuse-and-privilege-escalation/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.
PE3Reaches for credential files — false positiveRMRecursive force delete — false positiveNETMakes network calls — 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.