pydantic-ai

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of the pydantic-ai library and its dependencies from PyPI, which is a well-known service. These references are informative and facilitate standard development workflows.
  • [REMOTE_CODE_EXECUTION]: Documentation files reference the use of the Model Context Protocol (MCP) to execute external tools using npx. The specific packages highlighted (e.g., @modelcontextprotocol/server-filesystem) are from a well-known service and are part of the framework's intended functionality.
  • [COMMAND_EXECUTION]: The skill includes a scripts/check-updates.py utility designed to verify local file integrity and query the PyPI API for framework updates. These operations are restricted to standard version checking and filesystem verification.
  • [TIME_DELAYED_CONDITIONAL]: The included maintenance script contains logic to identify documentation that has not been updated for 90 days. This is an administrative freshness check for the documentation and contains no malicious triggers.
  • [SAFE]: All code snippets provided in the reference files are for educational and implementation purposes, following Pydantic's best practices for type safety and input validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:30 AM
Security Audit — agent-trust-hub — pydantic-ai