c4-diagram-generator

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches diagram templates and utilizes remote rendering services.
  • Fetches PlantUML C4 macros from the plantuml-stdlib repository on GitHub.
  • Utilizes the Kroki.io service for remote diagram rendering via HTTP POST requests.
  • [COMMAND_EXECUTION]: The skill invokes several external command-line tools to process and export diagrams.
  • Executes structurizr-cli for workspace export and DSL processing.
  • Invokes mmdc (Mermaid CLI) for generating SVG, PNG, or PDF artifacts.
  • Runs java -jar plantuml.jar for local diagram rendering.
  • [INDIRECT_PROMPT_INJECTION]: The skill's feature to analyze source code for diagram generation creates an ingestion point for untrusted data.
  • Ingestion points: The analyze command reads files from the specified source directory as described in SKILL.md and README.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided.
  • Capability inventory: The skill utilizes Bash for tool execution, file system tools (Read, Write, Edit), and WebFetch for network access.
  • Sanitization: No sanitization process for the ingested source code content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:13 PM