Agent-Media UGC Video

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill facilitates data transmission to api.agent-media.ai, which is the service endpoint for the Agent-Media UGC tool. This is categorized as a safe, vendor-managed communication.
  • [PROMPT_INJECTION]: The skill processes user-supplied text to generate video content, creating a surface for indirect prompt injection.
  • Ingestion points: Parameters like script, person, and name are derived from user input.
  • Boundary markers: No specific delimiters or warnings are used to isolate user content.
  • Capability inventory: Capabilities are limited to video generation via the mcp__agent-media__make_ugc tool.
  • Sanitization: Input content is passed to the generation pipeline without additional filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 01:25 AM
Security Audit — agent-trust-hub — Agent-Media UGC Video