macos-native-review
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill reads only the user’s PRD/spec/plan artifacts (including their user-facing strings) plus first-party Apple HIG pages via WebFetch, and it does not describe ingesting outsider-authored free text from monitored feeds/queues without selecting spec text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to WebFetch Apple HIG pages at runtime (e.g., "verify by WebFetching the HIG page (WebFetch)"), so developer.apple.com URLs such as https://developer.apple.com/design/human-interface-guidelines/buttons are runtime dependencies that directly control the agent's citations and outputs.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata