stitch-design-md
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches HTML source code and screenshots from remote URLs provided by the Stitch platform to perform design system analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external HTML content which constitutes an attack surface where malicious instructions could be embedded by a project owner to influence the agent's behavior during documentation generation.
- Ingestion points: Processes content from external downloadUrl locations as specified in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded prompts are present in the analysis logic.
- Capability inventory: The skill utilizes the Write tool to generate the DESIGN.md file and Stitch MCP tools to query project information.
- Sanitization: There is no evidence of sanitization or filtering of the retrieved HTML content before it is processed by the agent.
Audit Metadata