penpot-design-to-code-review

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow can ingest outsider-authored free text from the user/another MCP as the “code source” (filesystem/pasted component code/Storybook DOM+CSS), which is then parsed in Phase 3 and used to generate the LLM-visible DRIFT report in Phase 4.