TypeScript SDK Reference

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References the @anthropic-ai/claude-agent-sdk NPM package. This resource is maintained by a trusted organization and is considered safe for use.
  • [COMMAND_EXECUTION]: Documents the functionality of the Bash tool, which is an intended core capability of the SDK for executing shell commands.
  • [PROMPT_INJECTION]: References the bypassPermissions mode for tools. This is documented as a configuration option for specific environments (such as CI/CD) and is consistent with the skill's purpose as an SDK reference.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 01:22 AM