pi-agent-core

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill content consists of technical documentation and reference guides for an AI agent framework.
  • [EXTERNAL_DOWNLOADS]: The documentation references Node.js packages such as @mariozechner/pi-agent-core, @mariozechner/pi-ai, and @sinclair/typebox as required dependencies for the framework.
  • [COMMAND_EXECUTION]: Code examples illustrate how to define tools using standard Node.js APIs (e.g., fs.promises.readFile). These are provided as benign implementation examples.
  • [PROMPT_INJECTION]: The framework includes safety features such as the beforeToolCall hook, which allows developers to intercept and block potentially dangerous tool calls, demonstrating a security-conscious design.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 02:30 PM
Security Audit — agent-trust-hub — pi-agent-core