youtube-content
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation requires the installation of the
youtube-transcript-apipackage to fetch transcript data from YouTube. - [COMMAND_EXECUTION]: The skill utilizes a local script
scripts/fetch_transcript.pyto interact with the YouTube API and retrieve content for processing. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes raw transcript text from untrusted external videos.
- Ingestion points: Transcript content fetched from YouTube URLs via the
fetch_transcript.pyscript as described in SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" wrappers are mentioned in the workflow to separate transcript data from agent instructions.
- Capability inventory: The skill can generate summaries, blog posts, and Twitter threads, which involves processing the entire content of the ingested transcript.
- Sanitization: The workflow does not include any sanitization or filtering steps to identify or neutralize potential malicious instructions embedded in the transcripts.
Audit Metadata