captions

Warn

Audited by Snyk on Apr 29, 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). This skill explicitly fetches YouTube transcripts from a third‑party service (SKILL.md: "Extract closed captions from YouTube videos via TranscriptAPI.com" and the documented GET /api/v2/youtube/transcript), which are public/user-generated, are ingested and read by the agent for quoting/translation/summarization, and therefore could contain untrusted instructions that materially influence the agent's outputs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:58 AM
Issues
1