transcribing-youtube

Warn

Audited by Snyk on Mar 1, 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 directly fetches and ingests public YouTube subtitles and metadata via yt-dlp (see scripts/genInfoNugget.sh with --write-subs/--write-auto-subs and SKILL.md's workflow that tells the agent to "read the prose file and summarize by chapter"), so untrusted, user-generated content from the open web is read and used to drive summaries/decisions, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 03:44 PM