artifact-capabilities
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a comprehensive reference for a sandboxed runtime environment, providing TypeScript definitions and usage instructions for built-in capabilities.
- [EXTERNAL_DOWNLOADS]: Mentions fetching configuration data from an official Anthropic API endpoint (api.anthropic.com) for Model Context Protocol (MCP) server integration. As Anthropic is a trusted organization, this reference is legitimate and safe.
- [CREDENTIALS_UNSAFE]: References the use of an environment variable (
$CLAUDE_CODE_OAUTH_TOKEN) for API authentication in developer examples. This is standard development practice and does not involve hardcoded secrets. - [DATA_EXFILTRATION]: The documented APIs incorporate privacy-preserving features, such as opaque, scope-limited user identifiers and warnings against storing sensitive profile data in shared storage.
Audit Metadata