youtube-watch-later-gist-summaries

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses gh (GitHub CLI) to create gists and check authentication status. These are standard operations for the skill's stated purpose.
  • [REMOTE_CODE_EXECUTION]: The skill provides Python snippets to be executed via python3 - or uv run. These snippets are contained within the skill, are used to fetch transcripts using the youtube-transcript-api library, and do not execute untrusted external code.
  • [EXTERNAL_DOWNLOADS]: The skill suggests using uv run --with youtube-transcript-api to fetch transcripts if the library is missing. This is a standard package management practice and targets a well-known library.
  • [DATA_EXFILTRATION]: While the skill reads transcripts and sends summaries to GitHub, this is the core function of the skill. The instructions explicitly mandate creating 'secret' gists and warn against using the --public flag to prevent unauthorized data exposure.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns or attempts to bypass safety filters were detected in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 01:41 PM
Security Audit — agent-trust-hub — youtube-watch-later-gist-summaries