stream-transcript-processor
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches auto-generated captions from arbitrary public YouTube/Twitch URLs (see scripts/fetch_transcript.py and the "Full Pipeline (URL Provided)" in SKILL.md), then parses and scores that untrusted transcript to choose clips, draft posts, generate YouTube metadata, and trigger media-fetching — meaning third-party transcript content is ingested and can materially influence downstream actions.
Audit Metadata