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