swiftui-webkit

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides instructions for loading and interacting with remote web content, which presents a surface for indirect prompt injection.
  • Ingestion points: External data enters the agent's context through WebView(url:) and WebPage.load() functions defined in SKILL.md and references/wkwebview-fallback.md.
  • Boundary markers: The documentation explicitly instructs the implementation of WebPage.NavigationDeciding for host allowlisting and recommends routing off-domain links to the system browser.
  • Capability inventory: The skill manages significant capabilities including JavaScript execution (callJavaScript), script message handlers (userContentController), and custom URL schemes (URLSchemeHandler).
  • Sanitization: The instructions provide strong sanitization guidance, such as mandating the use of the arguments parameter for JavaScript calls to prevent string interpolation/script injection and utilizing WKContentWorld for execution isolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 09:00 PM
Security Audit — agent-trust-hub — swiftui-webkit