drawio-diagram

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to utilize the draw.io command-line interface for exporting diagrams to various image and document formats. It also uses standard platform commands such as open (macOS), xdg-open (Linux), and start (Windows) to display the generated files.
  • [EXTERNAL_DOWNLOADS]: The HTML export template provided in SKILL.md fetches a static viewer script from https://viewer.diagrams.net, which is the official domain for the diagrams.net (formerly draw.io) service.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its primary workflow of reading external repositories and documentation to generate diagram content.
  • Ingestion points: The workflow defined in SKILL.md involves reading source material such as repositories, documentation, and README files.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the external source material.
  • Capability inventory: The skill is capable of executing subprocesses via the draw.io CLI and performing file writing operations to the local filesystem.
  • Sanitization: While the skill recommends XML-escaping content for HTML embedding, this only protects the file structure and does not prevent the agent from following instructions embedded in the processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:49 AM
Security Audit — agent-trust-hub — drawio-diagram