agile-design
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill defines a standard process for design organization and documentation, utilizing stable IDs and paired notes to ensure traceability between planning artifacts and visual designs.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project planning files and existing design assets to guide the prototyping process, which represents a standard data ingestion surface for this type of workflow.
- Ingestion points: Reads requirement and story data from the
planning/directory, project-levelDESIGN.mdfiles, and existing design tool canvases. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the ingested data.
- Capability inventory: The skill has the capability to write to the project repository (creating README.md and notes) and to interact with external design tools via specialized MCP adapters as described in
references/tools.md. - Sanitization: No explicit validation or sanitization is performed on the ingested planning data before it is used to populate documentation or drive tool actions.
- [COMMAND_EXECUTION]: The skill orchestrates operations through various tool-specific adapters and MCP extensions (e.g., Paper MCP, Figma skills, Penpot MCP). These are standard platform integrations necessary for interacting with design software and do not involve high-risk command execution.
Audit Metadata