ios

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses a research agent that queries Context7/Exa for documentation, but does not ingest outsider-authored free text from an unselected source.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references Homebrew taps and installations for external tooling (such as cameroncooke/axe) via bash commands, representing an unofficial runtime dependency.