pi-coding-agent-extensions

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of technical documentation and code snippets designed to teach developers how to use the Pi Coding Agent extension system. All provided examples are benign and follow best practices.
  • [COMMAND_EXECUTION]: The documentation references built-in capabilities such as the bash tool and the pi.exec method. These are standard features of the agent environment intended for developer tasks and are described here for instructional purposes.
  • [REMOTE_CODE_EXECUTION]: The material describes the agent's use of the jiti library to load TypeScript modules at runtime. This is an architectural component of the Pi Coding Agent platform and not an exploit or malicious behavior within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 02:30 PM
Security Audit — agent-trust-hub — pi-coding-agent-extensions