tzai-icon
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill searches for a specific engine script within the user's home directories (~/.agents/, ~/.claude/, etc.) and executes it using bash.
- [PROMPT_INJECTION]: The skill incorporates user-provided text into shell command arguments for icon generation. 1. Ingestion points: User visual brief prompt captured in SKILL.md. 2. Boundary markers: None present in the execution logic. 3. Capability inventory: Shell command execution via bash. 4. Sanitization: No explicit sanitization of user content before interpolation into the engine call.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to install dependencies from the vendor's repository using the npx command if the local engine is not found.
Audit Metadata