baoyu-diagram

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local TypeScript script (scripts/main.ts) to handle the conversion of SVG diagrams to PNG files. This script is executed by the agent using the Bun runtime or npx as part of the diagram generation workflow.
  • [EXTERNAL_DOWNLOADS]: The skill fetches typography resources from Google Fonts (fonts.googleapis.com) and instructs the agent to potentially download the Bun runtime via npx if it is not already available on the system.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing user-provided text and uploaded content to generate diagrams without sufficient safeguards.
  • Ingestion points: User prompts and uploaded files serve as the primary input for diagram generation (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or provide specific prompts to the agent to ignore instructions embedded within the processed data.
  • Capability inventory: The skill has capabilities for local file system writes and the execution of a helper script (scripts/main.ts).
  • Sanitization: No sanitization, escaping, or validation of the input data is performed before it is interpolated into the SVG structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:05 AM
Security Audit — agent-trust-hub — baoyu-diagram