photoreal-image
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill includes shell scripts
generate.shandinstall-everywhere.shto facilitate the image generation workflow and skill installation. These scripts perform standard operations such as creating symlinks in~/.local/binand updating agent configuration files likeAGENTS.mdandGEMINI.mdto point to the skill instructions. - [EXTERNAL_DOWNLOADS]: The
generate.shutility makes network requests to official endpoints for Google Gemini, OpenAI, and Black Forest Labs (api.bfl.ai). These requests are used to transmit prompt data and receive generated images, which is the primary intended function of the skill. - [SAFE]: The skill exhibits secure development practices, including the use of
jqfor safe JSON construction and reliance on user-provided environment variables for API authentication. No evidence of obfuscation, malicious persistence, or unauthorized data access was found during the analysis.
Audit Metadata