code-to-diagram

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs command execution using 'mmdc' for rendering diagrams and 'git clone' for fetching codebase repositories.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from remote Git repositories and references the '@mermaid-js/mermaid-cli' package from the official NPM registry.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted codebase data. Ingestion points: Code read via 'glob' and 'read' operations, and repositories cloned from remote URLs as specified in 'SKILL.md'. Boundary markers: None identified. Capability inventory: Command execution ('git', 'mmdc') and file system access ('read', 'write'). Sanitization: No explicit sanitization of ingested code content is performed before generating Mermaid syntax.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:57 PM