youtube-video-analyst
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation and use of the
youtube-transcript-apiPython library to retrieve transcript data from YouTube. - [COMMAND_EXECUTION]: The skill provides instructions for the user to execute a local script,
fetch_transcript.py, which processes YouTube URLs via the command line. - [PROMPT_INJECTION]: The skill processes untrusted transcript data from external videos, which creates a surface for indirect prompt injection attacks. * Ingestion points: Data is ingested through the execution of
fetch_transcript.pyor through manual pasting by the user into the agent's context. * Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat the transcript content as untrusted data or to ignore embedded commands. * Capability inventory: The skill is intended for use alongside content creation tools, potentially allowing malicious transcript instructions to influence downstream content generation. * Sanitization: The provided scripts and instructions contain no logic for sanitizing, validating, or filtering the content of the fetched transcripts before analysis.
Audit Metadata