videodb-skills
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to ingest videos from public sources (e.g., "Upload https://www.youtube.com/watch?v=..." and "Upload any video... from YouTube, URLs"), so the skill fetches untrusted, user-generated content that the agent reads/transcribes/searches and which could contain instructions that influence subsequent actions.
Audit Metadata