youtube-analytics

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts 'analytics.py' and 'preflight.py' via 'python3'. It includes a bash command to change directory to an absolute path '/Users/gaebalai/Workspace2/youtube-bgm-auto' and activate a virtual environment.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external channel and video metadata from the YouTube API. 1. Ingestion points: Video and channel data fetched via 'analytics.py'. 2. Boundary markers: Not specified. 3. Capability inventory: Subprocess execution and local file writing. 4. Sanitization: None mentioned for API content.
  • [CREDENTIALS_UNSAFE]: The skill identifies and verifies sensitive files, specifically OAuth credentials and a 'PIXABAY_KEY', through its preflight validation script. Accessing or managing such sensitive credential files presents a risk of exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:57 PM
Security Audit — agent-trust-hub — youtube-analytics