content-auditor
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified during the analysis of the skill. The logic is restricted to content evaluation and uses standard file-handling tools as defined in the frontmatter configuration.
- [PROMPT_INJECTION]: The skill processes external content for auditing, which is an inherent surface for indirect prompt injection. However, given the skill's specific purpose and lack of autonomous execution logic, this is documented as an inherent architectural property rather than a malicious finding.
- Ingestion points: User-provided content (via Read, Grep, and Glob tools).
- Boundary markers: Absent.
- Capability inventory: File system access (Read, Write, Edit, Grep, Glob).
- Sanitization: Absent.
Audit Metadata