anthropic-managed-agents
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a purely instructional guide and design tool for configuring Anthropic Managed Agents. It does not contain any instructions that attempt to bypass safety filters or override agent behavior.
- [SAFE]: No hardcoded credentials, sensitive file access, or unauthorized network operations were detected. The skill correctly directs users to manage authentication through Anthropic's vault system as per official documentation.
- [SAFE]: All external references point to official Anthropic documentation (platform.claude.com) or the author's GitHub repository for installation purposes, which are standard for AI agent skills.
- [SAFE]: No obfuscated code, hidden URLs, or dynamic execution patterns were found. The skill uses a clear reference structure with a separate primer file to maintain transparency.
Audit Metadata