use-js-interop

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an example of a clipboard monitor that reads text from the system clipboard. This represents a data ingestion surface where untrusted input enters the application context.
  • Ingestion points: navigator.clipboard.readText() in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: JavaScript to .NET bridge via [JSInvokable] methods.
  • Sanitization: Absent in the provided code snippet.
  • [DYNAMIC_EXECUTION]: The skill demonstrates the use of dynamic import for loading JavaScript modules. The implementation uses static constants for paths, which is a safe practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 09:31 AM
Security Audit — agent-trust-hub — use-js-interop