diagrama-mermaid

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions of systems and architectures to generate visual diagrams. This represents a surface where untrusted data enters the agent context.
  • Ingestion points: User requirements provided in Step 1 as described in SKILL.md.
  • Boundary markers: The skill instructions mandate the use of ```mermaid ``` blocks to clearly delimit generated code from natural language responses.
  • Capability inventory: The skill does not invoke any subprocess calls, file-write operations, or network tools; it primarily generates text-based Mermaid code.
  • Sanitization: No explicit sanitization is described, but the skill's mandatory interactive questioning phase (Step 2) acts as a natural filter for intent validation.
  • [EXTERNAL_DOWNLOADS]: The skill documentation and instructions reference external links to the official Mermaid Live Editor (mermaid.ai) and the official project repository on GitHub. These are well-known services within the developer ecosystem used for rendering and developing diagrams.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:24 PM
Security Audit — agent-trust-hub — diagrama-mermaid