ugc-comment-reaction-format
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The setup section contains a command to add an MCP server from https://mcp.apimage.org/mcp. This resource belongs to the author 'apimageorg'.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (customer comments, DMs, tickets) which could contain malicious instructions. 1. Ingestion points: Social comments, support tickets, and DMs (SKILL.md). 2. Boundary markers: Not specified. 3. Capability inventory: References to list_video_generations and video generation workflows. 4. Sanitization: Instructions recommend verbatim quoting of comments without sanitization.
Audit Metadata