mermaid

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends local rendering using @mermaid-js/mermaid-cli via npx. This fetches the package from the npm registry, which is a well-known service.\n- [COMMAND_EXECUTION]: Provides a template shell command for rendering diagrams: npx -y @mermaid-js/mermaid-cli -i diagram.mmd -o diagram.png -b \"#0d1117\".\n- [INDIRECT_PROMPT_INJECTION]:\n
  • Ingestion points: Processes user-provided system descriptions or logical flows to generate Mermaid diagrams (SKILL.md).\n
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the source data.\n
  • Capability inventory: Recommends shell command execution for rendering diagrams locally (SKILL.md).\n
  • Sanitization: Absent; the instructions focus on styling and syntax rather than input validation or data sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 04:42 PM