design-an-interface
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8c) when processing data from external tools.\n
- Ingestion points: Step 2 gathers context from Figma URLs, Linear issues, and Notion documents.\n
- Boundary markers: There are no delimiters or instructions to ignore instructions found within external documents.\n
- Capability inventory: Uses Task tool for sub-agents and MCP tools for data fetching.\n
- Sanitization: No sanitization is performed on external inputs before they are incorporated into prompts.\n- [EXTERNAL_DOWNLOADS]: The skill references and retrieves data from well-known external services.\n
- References: Integrates with Figma, Linear, and Notion to pull in project-related context and design documentation.
Audit Metadata