youtube-transcript
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (video transcripts) that could contain malicious instructions meant to manipulate the agent's behavior.
- Ingestion points:
transcript.jsretrieves transcript text from YouTube via theyoutube-transcript-plusdependency. - Boundary markers: The output format (
[timestamp] text) provides minimal structure but lacks explicit delimiters or instructions to the agent to treat the transcript content as data rather than instructions. - Capability inventory: The skill has network access via the transcript fetching tool.
- Sanitization: The script performs no sanitization, escaping, or filtering of the transcript content before outputting it to the agent context.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
youtube-transcript-pluspackage from the npm registry during the setup process.
Audit Metadata