gpui-component

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch documentation and component API references from https://gpui-kit.com via arbitrary .md URLs or llms-full.txt, which exposes the agent to untrusted web content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill documentation suggests fetching runtime dependencies and component documentation from external URLs like https://gpui-kit.com/llms-full.txt to control agent instructions or guide behavior.