oma-image

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute subprocesses using the codex CLI (codex exec) and the gemini CLI. These executions are core to the skill's function of routing image generation requests to different vendors.
  • [EXTERNAL_DOWNLOADS]: Accesses external content from the YouMind-OpenLab GitHub organization's repositories (e.g., awesome-gpt-image-2 and awesome-nano-banana-pro-prompts) using the GitHub CLI (gh api) to retrieve markdown documentation and prompt engineering templates.
  • [DATA_EXFILTRATION]: Reads from local application-specific directories such as ~/.claude/image-cache/ and ~/.codex/generated_images/ to process images that users have attached or previously generated, which is necessary for its stated 'reference image' functionality.
  • [EXTERNAL_DOWNLOADS]: Communicates with the Pollinations API (gen.pollinations.ai) and Google's Generative Language API for remote image generation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 01:32 AM