What the reviewer found
A CTF/red-team playbook for AI/LLM exploitation (prompt injection, jailbreaks, DAN, MCP tool abuse); every flagged string is an example payload to fire at a target, not an instruction to the installing agent. Dual-use offensive-security content, not malware against the installer.
dual-use— a security tool that can be misusedprompt-injection— tries to steer the agentexample-or-fixture— an example or test fixture
What was read
The file as it ships in 1ikeadragon/awesome-offsec-claude:
ai_attacks/SKILL.md
What the static scan said
The scan flagged 7things. The reviewer kept 0 and dismissed 7 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveP6Asks the agent to reveal its instructions — false positiveAR3Nullifies safety policies — false positivePE3Reaches for credential files — false positiveNETMakes network calls — false positiveSHRuns shell commands — false positive
How this review was made
Fable 5.1 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.