draw-io

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill executes a bash script (convert-drawio-to-png.sh) that invokes the drawio CLI for image conversion and uses git add to automatically stage generated PNG files. This is a legitimate functional requirement for the intended workflow but grants the agent the capability to modify the repository's git index.
  • PROMPT_INJECTION (LOW): The skill is designed to parse and manipulate .drawio XML files which contain user-controlled text elements. This represents an indirect prompt injection surface (Category 8) where malicious instructions could be embedded in diagram labels to influence agent behavior during processing.
  • Ingestion points: .drawio XML files are directly read and edited by the agent as part of its layout adjustment tasks.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when the agent processes the XML content.
  • Capability inventory: The agent has the ability to execute shell scripts, run the drawio CLI, and modify the git state via git add.
  • Sanitization: The skill does not perform sanitization or validation of the XML text content before the agent interprets it for layout calculations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM