skill-safety-audit
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (other skills, scripts, and assets) as part of its primary audit function, which creates a surface for indirect prompt injection. * Ingestion points: The skill accepts a changed skill folder, SKILL.md, scripts, and references as input for analysis (defined in the Required Input section). * Boundary markers: The instructions do not specify the use of delimiters or specific markers to distinguish between the auditor's instructions and the content being audited. * Capability inventory: The skill is primarily diagnostic; it analyzes files and returns a report. It does not contain instructions for network operations, file writes, or command execution. * Sanitization: The instructions do not include steps for sanitizing or escaping the content being audited before processing.
Audit Metadata