greenlight
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill fetches and interprets developer-supplied App Store metadata via the App Store Connect API (internal/asc/*.go → GetVersionLocalizations/GetAppStoreVersions) and it also performs HTTP GETs on arbitrary Support/Marketing URLs from that metadata (internal/checks/tier1_metadata.go checkURLReachability), so it ingests untrusted third‑party content (developer-provided metadata and public URLs) that the agent reads and analyzes.
Audit Metadata