qqbot-media
Warn
Audited by Snyk on Mar 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly accepts absolute http URLs in (e.g., "https://example.com/video.mp4") and states user-sent images are auto-downloaded and user voice may be STT-transcribed, meaning the agent will ingest untrusted third-party/user-generated media that can be interpreted and influence its subsequent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata