skills/mrecek/skills/yt-transcript/Gen Agent Trust Hub

yt-transcript

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests transcripts from YouTube, which constitutes an indirect prompt injection surface. Content provided by third-party video authors could potentially include instructions designed to influence the AI agent's behavior when it reads the generated markdown artifact.
  • Ingestion points: Untrusted transcript data is ingested via the script file using yt-dlp, youtube-transcript-api, and openai-whisper.
  • Boundary markers: The skill formats output as a structured Markdown file using headers and separators (e.g., ---), which helps the agent distinguish between metadata and the transcript body.
  • Capability inventory: The script performs network operations to fetch metadata and media, and it writes files to the local filesystem using tempfile and os.replace for atomic updates.
  • Sanitization: The script includes a redact_sensitive_text function to prevent proxy credentials from appearing in error logs and uses regular expressions to strip HTML tags and normalize content from VTT subtitle files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:30 PM