space-brand-ui-design

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md Step 2/3 runs npx getdesign@latest add <slug> and then cat /tmp/design-md-tmp/DESIGN.md, so the agent ingests outsider-authored free text fetched at runtime from the public getdesign.md/npm source into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runs the npx command at runtime to fetch and execute the getdesign package and then reads the generated DESIGN.md to drive prompts/outputs, which ties it to the external project at https://getdesign.md.