pexels-footage

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads media files from official Pexels API endpoints (api.pexels.com) using search terms provided to the script.
  • [COMMAND_EXECUTION]: A bash wrapper (pexels-footage.sh) is used to invoke the core Python logic (scripts/pexels_search.py).
  • [PROMPT_INJECTION]: The skill processes untrusted metadata from Pexels (photographer names, alt text) in scripts/pexels_search.py. Ingestion occurs via API responses, boundary markers are absent, and capabilities include file-writing and network access. Sanitization is limited to filename prefixing.
  • [SAFE]: PEXELS_API_KEY is managed via environment variables and sent exclusively to official Pexels endpoints. No persistence, obfuscation, or unauthorized access mechanisms were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 06:38 AM
Security Audit — agent-trust-hub — pexels-footage