Expo UI Jetpack Compose

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow instructs the agent to fetch external Expo documentation pages from https://docs.expo.dev/... (public web content), which can include free-form text that the agent then ingests into the LLM context (indirect prompt injection risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to fetch runtime docs from https://docs.expo.dev/versions/v55.0.0/sdk/ui/jetpack-compose/{component-name}/index.md and https://docs.expo.dev/versions/v55.0.0/sdk/ui/jetpack-compose/modifiers/index.md to confirm APIs before generating code, so remote content would directly control the agent's prompts/instructions.