claude-api-in-prototypes

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation for a built-in platform helper (window.claude.complete) that allows HTML artifacts to interact with Claude models without external SDKs.
  • [SAFE]: No prompt injection, data exfiltration, or obfuscation patterns were detected. The described functionality, including client-side tool execution, is presented as a legitimate feature of the development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 12:42 PM
Security Audit — agent-trust-hub — claude-api-in-prototypes