claude-agent-sdk

Warn

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The file templates/custom-mcp-server.ts includes a calculate tool implementation that uses the JavaScript eval() function to process expression strings provided by the agent. While the template includes a warning comment advising the use of a proper math parser for production, the inclusion of eval() with direct input from the agent represents a significant security risk for arbitrary code execution if developers copy the code verbatim.
  • [EXTERNAL_DOWNLOADS]: The documentation and setup scripts (SKILL.md, scripts/check-versions.sh, and templates/package.json) reference the installation of several external dependencies from the official npm registry, including @anthropic-ai/claude-agent-sdk, @anthropic-ai/claude-code, and zod. These downloads originate from official sources and are documented as required for the SDK's functionality.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 18, 2026, 02:14 PM
Security Audit — agent-trust-hub — claude-agent-sdk