drawio-skill
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several local commands including the
draw.ioCLI for rendering diagrams,python3for running utility scripts, andgitfor update management and version checking. It also uses standard system utilities likemkdir,rm,mv, and platform-specific commands to open the desktop application (open,xdg-open,start).- [EXTERNAL_DOWNLOADS]: It communicates with the vendor's GitHub repository to check for available updates and offers to perform agit pullif a newer version is found, which requires user consent. It also provides installation instructions pointing to official GitHub releases and Homebrew for the requireddraw.iodesktop application.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) because it extracts labels and styling from user-provided.drawiofiles and images to create new diagrams. - Ingestion points: The style extraction process in
references/style-presets.mdandreferences/style-extraction.mdreads content from external XML files and images. - Boundary markers: There are no specific delimiters used for the ingested label text in the generated XML, but the skill emphasizes XML entity escaping.
- Capability inventory: The skill can execute shell commands, write files locally, and initiate network version checks.
- Sanitization: The instructions explicitly direct the agent to escape XML special characters and provide an approval loop where the user reviews a sample diagram before any extracted style is saved.
Audit Metadata