tzai-moodboard

Warn

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically locates an executable script by searching through several hidden directories in the user's home folder (e.g., .agents/skills/, .claude/skills/) and executes the found path using bash.
  • [COMMAND_EXECUTION]: The skill is vulnerable to command injection through the interpolation of user data into a shell command. 1. Ingestion points: The placeholder in the Run section. 2. Boundary markers: The prompt is enclosed in double quotes, which can be bypassed using shell metacharacters. 3. Capability inventory: The skill has the capability to execute bash commands. 4. Sanitization: No sanitization or escaping mechanisms are implemented for the external input.
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing a required dependency from the author's GitHub repository using the command 'npx skills add kedoupi/tzai-image-skill'.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 02:50 AM
Security Audit — agent-trust-hub — tzai-moodboard