youtube-video-analyst
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes YouTube transcripts, which are external, untrusted data sources that could contain malicious instructions designed to hijack the agent's behavior.
- Ingestion points: Transcripts fetched via
scripts/fetch_transcript.pyor manually pasted into the context. - Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore embedded commands within the transcript data.
- Capability inventory: The skill has the ability to execute a local Python script with network access and file system write capabilities.
- Sanitization: No sanitization or filtering is applied to the transcript text before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill utilizes a Python script (
scripts/fetch_transcript.py) to fetch data from YouTube. The script is used for its intended purpose and does not exhibit malicious command patterns, but it is a point of interaction with the host system. - [EXTERNAL_DOWNLOADS]: The included script depends on the
youtube-transcript-apiPython library. While a standard package for this task, it represents an external dependency that must be installed on the host.
Audit Metadata