visualize-plan
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references font assets from Google Fonts (fonts.googleapis.com) and the Mermaid diagram library from the JSDelivr CDN (cdn.jsdelivr.net). These are well-known services used for standard web document presentation.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use local Python scripts (check_plan_page.py and build_standalone.py) to perform validation and wrap HTML fragments into standalone documents. These scripts operate on local files within the skill's workspace.
- [INDIRECT_PROMPT_INJECTION]: The skill processes implementation plans from plan.md to generate HTML. 1. Ingestion points: plan.md file content. 2. Boundary markers: Instructions tell the agent to stick to the plan and write plainly, but no technical markers are in the output. 3. Capability inventory: Writing local files and executing skill-provided Python scripts. 4. Sanitization: Structural checks are performed by check_plan_page.py, but content is not sanitized.
Audit Metadata