tzai-mindmap

Fail

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill searches for and executes a bash script found within the user's home directory subfolders, specifically targeting paths like ~/.agents/skills/tzai-image/scripts/tzai-image or ~/.claude/skills/tzai-image/scripts/tzai-image.
  • [REMOTE_CODE_EXECUTION]: The logic is vulnerable to command injection because user input (subject) is interpolated directly into a shell command: bash "$ENGINE" mindmap --prompt "". A malicious or crafted user input containing shell metacharacters such as ; or ` could be used to execute arbitrary commands on the host system.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install an external dependency from the author's repository using the command npx skills add kedoupi/tzai-image-skill.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 10, 2026, 02:49 AM
Security Audit — agent-trust-hub — tzai-mindmap