explicit-checker
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes track lyrics which constitute untrusted external data. Although lyrics could contain malicious instructions, the skill uses specific word-list analysis and reporting which mitigates risk. * Ingestion points: Lyrics fetched via the extract_section tool mentioned in SKILL.md. * Boundary markers: None. * Capability inventory: Restricted to metadata reading and text scanning via bitwize-music-mcp. * Sanitization: The skill performs targeted scanning for a defined list of profanity.
Audit Metadata