Security audit
Security checks for vulnerabilities and agentic risk
This is a text-analysis skill that extracts principles from user-provided content and does not include executable code or external service calls.
This skill is appropriate for extracting and organizing ideas from text. Before installing, note that it may process sensitive pasted content through whatever model provider your agent is already configured to use, and the maintainer should clarify the requires_review.md wording so users are not confused about whether review artifacts are written to disk.
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
### The Extraction Process
**Bootstrap**: Read source material without judgment
**Learn**: Identify patterns, test for invariance
**Enforce**: Validate through rephrasing test
The skill states it does not write files, but later instructs that drifted normalization cases be added to requires_review.md, creating a contradictory data-handling promise. This can mislead operators about persistence behavior and cause unintended storage of potentially sensitive user-derived content if an agent implementation follows the schema literally.
No suspicious patterns detected.