subtitles

Warn

Audited by Snyk on Apr 28, 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 explicitly fetches YouTube video transcripts from a public third-party service (see SKILL.md: "Fetch YouTube video subtitles via TranscriptAPI.com" and the GET /api/v2/youtube/transcript endpoint), which are user-generated/untrusted contents that the agent is expected to read and use for translation/processing, so those transcripts could indirectly inject instructions affecting the agent's actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 09:19 PM
Issues
1