videodb

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). The skill explicitly ingests arbitrary public URLs, YouTube links, and RTSP/RTMP streams and consumes real-time WebSocket events (see SKILL.md "Common inputs", reference/api-reference.md coll.upload and coll.connect_rtstream, reference/rtstream-reference.md, and scripts/ws_listener.py), and those untrusted third‑party contents are parsed/indexed and used to drive searches, timeline edits, alerts, and other agent actions—so they can materially influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 11:44 AM