drawio
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided descriptions to generate mxGraphModel XML, creating an indirect prompt injection surface.
- Ingestion points: User instructions provided via the
/drawiocommand or natural language diagram requests are used to generate XML content (SKILL.md). - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to the agent to disregard instructions that might be embedded within the user's diagram description.
- Capability inventory: The skill utilizes the
Bashtool for command execution and theWritetool for file creation (SKILL.md). - Sanitization: No explicit sanitization, validation, or escaping of the user-provided data is defined before it is used to generate the XML structure.
- [COMMAND_EXECUTION]: The skill executes local shell commands to facilitate diagram processing and viewing.
- Invokes the
draw.iodesktop CLI (e.g.,/Applications/draw.io.app/Contents/MacOS/draw.ioordrawio.exe) to export XML to formats like PNG, SVG, or PDF (SKILL.md). - Uses platform-specific commands such as
open,xdg-open, andstartto launch the generated files in the system's default viewer (SKILL.md).
Audit Metadata