mermaid-diagramming

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is instructional and provides syntax references for Mermaid diagramming. It contains no executable scripts or requests for sensitive information.
  • [NO_CODE]: The skill consists entirely of markdown documentation and references, with no accompanying scripts or executables.
  • [PROMPT_INJECTION]: The skill processes user-provided technical descriptions to generate diagrams and utilizes the Read and Write tools. This ingestion surface lacks explicit boundary markers or sanitization for potential embedded instructions within user data.
  • Ingestion points: User descriptions provided to the agent for diagram generation (e.g., process flows, architecture details).
  • Boundary markers: None identified in the provided skill instructions.
  • Capability inventory: Read and Write tools for interacting with documentation files.
  • Sanitization: No explicit sanitization or validation of the generated Mermaid code or input data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:58 AM