youtube

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and search.py explicitly fetch and parse search results from the public Invidious API at https://yt.tarka.dev/api/v1/search, which returns untrusted, user-generated YouTube content that the agent reads and uses to decide which videos/links to present.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 02:42 AM