integrate-arcjet-guard-claude-managed-agents-py
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides integration instructions for a security product (Arcjet) into a specific platform (Anthropic Claude Managed Agents).
- [SAFE]: The skill uses environment variables (
os.environ["ARCJET_KEY"]) for managing API keys, which is a standard security best practice to prevent credential leakage. - [SAFE]: The skill implements security measures specifically designed to detect and block prompt injection attacks using the
DetectPromptInjectionrule. - [EXTERNAL_DOWNLOADS]: Fetches dependencies
arcjetandanthropicfrom official package registries. These are legitimate resources provided by the vendor and a trusted platform provider.
Audit Metadata