claude-agent-sdk
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and code examples for the official Anthropic Claude Agent SDK. All referenced packages and URLs are official Anthropic resources or belong to well-known technology services such as GitHub, Slack, and Playwright.- [SAFE]: The skill provides explicit security guidance, documenting patterns for command filtering, audit logging, and sandbox redirection to ensure developers build secure agentic workflows.- [SAFE]: The binary .skill file is a standard compressed archive containing the markdown source files and references provided in the skill structure.
Audit Metadata