agent-sdk-definitions

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational, providing templates and examples for programmatic agent definitions using the Claude Agent SDK.
  • [EXTERNAL_DOWNLOADS]: References official Anthropic SDK packages (@anthropic-ai/claude-agent-sdk and claude_agent_sdk), which are from a well-known and trusted organization.
  • [COMMAND_EXECUTION]: While the examples include tools like Bash and Write in the configuration, these are standard parameters for the SDK being documented and do not involve unauthorized or hidden command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:52 AM
Security Audit — agent-trust-hub — agent-sdk-definitions