character-design-sheet
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill utilizes the 'allowed-tools' frontmatter field to restrict the 'Bash' tool to only execute 'infsh' commands. This is a robust security measure that prevents the agent from running arbitrary shell commands outside the intended scope of the inference.sh platform.
- [COMMAND_EXECUTION]: All shell commands provided (infsh login, infsh app run, infsh app list) are specific to the tool's core functionality for authenticating and generating AI images. There is no evidence of command injection or usage of sensitive arguments.
- [EXTERNAL_DOWNLOADS]: The skill references installation documentation hosted on GitHub for the inference.sh CLI. This is a standard practice for developer tools and is presented neutrally as informational content for setup.
Audit Metadata