design-md
Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow uses Stitch MCP server tools to retrieve project metadata, screen details, and HTML code (`htmlCode.downloadUrl`), which is then fetched and parsed as free text by the LLM.
- Repository
whimzyLive/nightshift-ai
- Revision
44c1caf
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.