mimar

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the local repository context to generate architectural documentation. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
  • [DATA_EXFILTRATION]: While the skill reads project configuration files (e.g., package.json, go.mod), it does not perform network operations or attempt to transmit data to external servers.
  • [PROMPT_INJECTION]: The skill processes untrusted codebase files to generate summaries. This constitutes an indirect prompt injection surface; however, the risk is minimal as the script primarily extracts structural metadata rather than executing file contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 01:34 AM
Security Audit — agent-trust-hub — mimar