skills/spm1001/trousse/picture/Gen Agent Trust Hub

picture

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The imagen.sh script executes the macOS security utility to retrieve the Gemini API key from the system keychain. This is a recognized secure practice for handling credentials locally without exposing them in shell history or environment files.
  • [EXTERNAL_DOWNLOADS]: The Python script generate.py communicates with official Google Generative AI API endpoints to process image generation requests.
  • [DATA_EXFILTRATION]: The skill reads local image files for its editing features and writes generated images to a local ./images directory. These operations are consistent with the skill's stated purpose and do not involve unauthorized data movement.
  • [SAFE]: The code uses official, well-maintained libraries such as google-genai and Pillow. No patterns of obfuscation, persistence, or privilege escalation were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 08:46 AM
Security Audit — agent-trust-hub — picture