mermaid-mind-map
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and references are focused entirely on generating visual diagrams using Mermaid syntax. No malicious logic, obfuscation, or persistence mechanisms were found.
- [PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection by reading external files and codebases. However, the risk is minimal as the agent's capabilities are restricted to generating non-executable text and writing markdown files. Ingestion points: codebase config files (package.json, pyproject.toml) and user-specified documents. Boundary markers: absent. Capability inventory: generation of Mermaid syntax and markdown file writing. Sanitization: the skill instructs the agent to escape special characters to ensure correct Mermaid parsing.
Audit Metadata