What the reviewer found
An AI/LLM pentest playbook (garak, promptfoo, MSF) for authorized testing of chatbots and agents. Every DAN prompt, injection string, and SSRF-to-metadata example is a documented test technique against a placeholder "target", not an action the file itself carries out.
dual-use— a security tool that can be misused
What was read
The file as it ships in Suzu-Testing/metasploit-cursor-harness:
.cursor/skills/ai-llm-pentest/SKILL.md
What the static scan said
The scan flagged 8things. The reviewer kept 0 and dismissed 8 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveP6Asks the agent to reveal its instructions — false positiveAR3Nullifies safety policies — false positiveE1Sends data to an external URL — false positiveSSRF1Cloud metadata endpoint — 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.