What the reviewer found
An AI red-team methodology skill (Claude-HunterKit) documenting prompt-injection and jailbreak techniques (DAN, HTML-comment smuggling, exfiltration chains) as attack examples for authorized security testing, not instructions embedded to hijack the reviewing agent itself.
dual-use— a security tool that can be misused
What was read
The file as it ships in vigilantshield/Claude-HunterKit:
skills/ai/ai-01-prompt-injection/SKILL.md
What the static scan said
The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveP6Asks the agent to reveal its instructions — false positiveAR3Nullifies safety policies — 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.