threejs-app-director
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill does not contain instructions to override safety filters, bypass constraints, or ignore previous instructions. The instructional language is focused on project management and technical implementation.
- [DATA_EXFILTRATION]: No sensitive file paths, credential markers, or unauthorized network operations were detected. Mentions of 'Mint links' and 'remote world runtime' refer to the vendor's own assets and infrastructure (mintdotgg), which is consistent with the author's context.
- [REMOTE_CODE_EXECUTION]: The skill does not perform remote script execution or install unverified packages. It relies on internal project structure and referenced skill files for specialized tasks.
- [COMMAND_EXECUTION]: There are no instructions for dangerous shell command execution, privilege escalation (sudo/chmod), or persistence mechanisms.
- [OBFUSCATION]: No hidden content, encoded strings, homoglyphs, or zero-width characters were found in the skill or reference files.
Audit Metadata