mermaid-diagrams
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references standard tools and resources for the Mermaid ecosystem, such as the official Mermaid Live Editor and the @mermaid-js/mermaid-cli package. These are well-known and legitimate tools used for rendering and exporting diagrams.\n- [INDIRECT_PROMPT_INJECTION]: The skill documents interactive diagram features such as 'click' events and tooltips that could facilitate indirect prompt injection if an agent uses these features to visualize untrusted user data without proper sanitization.\n
- Ingestion points: User-provided technical descriptions, architectural requirements, or code snippets provided to the agent for visualization.\n
- Boundary markers: Absent.\n
- Capability inventory: Interactive 'click' events and 'link' tooltips described in references/advanced-features.md and references/sequence-diagrams.md.\n
- Sanitization: Absent.
Audit Metadata