image-generation

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the google-genai and Pillow Python packages. Both are official or widely-used libraries from trusted and well-known sources.
  • [CREDENTIALS_UNSAFE]: The documentation instructs users to set a GEMINI_API_KEY environment variable using a placeholder (your-api-key), which is a standard and safe practice for credential management.
  • [COMMAND_EXECUTION]: The skill provides usage examples for a local CLI tool tools/gemini-generate.py. The demonstrated commands are consistent with the skill's purpose of image generation and multi-turn refinement.
  • [PROMPT_INJECTION]: The skill ingests user prompts and images to generate AI content. This represents a typical input surface for generative AI tasks and does not contain any instructions that attempt to bypass safety guidelines or exfiltrate data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 07:37 PM
Security Audit — agent-trust-hub — image-generation