youtube-transcript
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes transcript data from an external, user-controlled source (YouTube).
- Ingestion points: The
transcript.jsscript fetches transcript text from YouTube via theyoutube-transcript-pluslibrary. - Boundary markers: The output is formatted with timestamps but lacks explicit delimiters or instructions to the agent to ignore instructions within the transcript text.
- Capability inventory: The script performs network requests to fetch data but does not include file system writes, subprocess execution, or other high-privilege operations.
- Sanitization: The script does not sanitize the transcript text for potential malicious instructions before outputting it to the agent.
Audit Metadata