process-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): This skill processes HTML comment markers from files to guide AI responses. * Ingestion points: User-provided file content via HTML comment markers. * Boundary markers: None defined in the provided file. * Capability inventory: Guiding agent actions and modifying file content. * Sanitization: None mentioned.
- No Code (SAFE): This skill definition contains only metadata and descriptive text, with no executable scripts or command execution.
Audit Metadata