mermaid-diagrams
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation and reference materials for software diagramming. No malicious patterns, obfuscation, privilege escalation, or persistence mechanisms were detected.
- [EXTERNAL_DOWNLOADS]: The documentation references standard and well-known tools and libraries for Mermaid rendering, which is expected for this type of skill. Specifically, it mentions the @mermaid-js/mermaid-cli NPM package and includes an HTML integration example referencing the official Mermaid library via jsdelivr.net.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interpret user requests to generate diagrams, which creates an inherent ingestion surface for external data.
- Ingestion points: User-provided descriptions of architectures, database designs, and processes as defined in SKILL.md.
- Boundary markers: None explicitly defined in the documentation files.
- Capability inventory: None. The skill does not possess executable capabilities, subprocess calls, or network operations.
- Sanitization: Not applicable as the skill provides static guidance.
Audit Metadata