codemermaid

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes Google Fonts, a well-known and trusted service, for its typography. References to these external resources are neutral and used solely for design purposes.
  • [SAFE]: Core functionalities like codebase scanning and HTML file generation are implemented using standard, predictable patterns as described in the instructional phases.
  • [PROMPT_INJECTION]: There is a potential surface for indirect prompt injection as the skill reads untrusted code and comments from repositories. However, the structured approach to analysis (Phase 1 and 2) and the requirement for verbatim code copies for 'code-walk' units significantly limit the likelihood of malicious instructions influencing the agent's behavior.
  • [SAFE]: The interactive features in the generated documentation, such as copying file paths and opening files in local IDEs (VS Code/Cursor), are implemented using safe, standard browser APIs and URI schemes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:38 AM
Security Audit — agent-trust-hub — codemermaid