drawio
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands using user-provided diagram names and export formats without explicit guidance on sanitization or escaping.
- Evidence: The skill uses user-supplied placeholders
<name>and<format>directly in shell command templates:drawio -x -f <format> -e -b 10 -o "<DRAWIO_OUTPUT_DIR>/<name>/<name>.drawio.<format>" <input.drawio>. - Risk: If a user provides a diagram name containing shell metacharacters (e.g.,
diagram; rm -rf /), the agent might execute unintended commands depending on the shell environment and how the agent handles theBashtool calls. - File Opening Risk: Similar risks exist for platform-specific file-opening commands (
open <file>,xdg-open <file>,start <file>) where the file path is partially derived from user input.
Audit Metadata