image-annotate

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill processes images locally using the established Pillow library and does not perform any network requests or data exfiltration.
  • [SAFE]: The Python script (scripts/annotate.py) safely parses JSON and CLI inputs without using dangerous execution functions like eval() or exec().
  • [SAFE]: The skill provides explicit security guidance on the difference between blurring and redaction, advising users to use solid blocks for sensitive data to prevent reconstruction.
  • [SAFE]: The skill requires the installation of Pillow from PyPI, which is a well-known and trusted package registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 12:27 PM
Security Audit — agent-trust-hub — image-annotate