swiftui-patterns

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is installing and invoking a community skill from a public GitHub repository (outsider-authored content), where the agent will fetch and read the skill’s runtime instructions/text from that upstream source to execute it.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run an install at runtime that fetches and executes code from the GitHub repo https://github.com/dimillian/Skills (via the provided "npx skills add dimillian/Skills --skill swiftui-ui-patterns" / "claude skills add dimillian/Skills" commands), which would load external skill content that can directly control prompts or execute code.