user-content-safety
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted user-generated content (posts, comments, reviews, and uploads), which represents an indirect prompt injection attack surface.
- Ingestion points: User-submitted content such as posts, comments, reviews, and profile bios as described in the 'Activate when' section of SKILL.md.
- Boundary markers: The skill explicitly instructs checking for sanitization and using inert test payloads to verify safety during the 'Verify' stage.
- Capability inventory: The skill advises the agent to perform actions such as modifying code to add sanitization, rate limits, and reporting links (file-write capabilities).
- Sanitization: The primary purpose of the skill is to identify missing sanitization and implement rendering safety (e.g., XSS prevention) for external content.
Audit Metadata