uml-diagram-design

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing 'node-plantuml' via npm and mentions downloading 'plantuml.jar'. These are standard, well-known tools used for generating UML diagrams from text.- [COMMAND_EXECUTION]: The documentation includes shell command examples for package management and tool execution (e.g., 'npm install -g node-plantuml', 'java -jar plantuml.jar'). These commands are consistent with the skill's stated purpose of assisting with UML design.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user requirements to generate architectural diagrams, which represents a potential injection surface.
  • Ingestion points: User-provided business logic, system requirements, and flow descriptions.
  • Boundary markers: The skill does not define specific delimiters to separate user data from agent instructions.
  • Capability inventory: The skill is configured with access to 'Bash', 'Read', 'Write', and 'Edit' tools.
  • Sanitization: No specific validation or sanitization instructions are provided for the user-supplied requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — uml-diagram-design