pi-coding-agent-sdk

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for the Pi Coding Agent SDK (@earendil-works/pi-coding-agent). It contains structured guidance on session management, resource loading, and tool definition without any malicious instructions.
  • [SAFE]: Technical recipes provided in the references follow security best practices, specifically recommending the use of environment variables and in-memory storage for secrets rather than hardcoding credentials.
  • [SAFE]: External references target official project documentation on GitHub (earendil-works), which are well-known and trusted sources for this specific development context.
  • [SAFE]: No patterns of prompt injection, obfuscation, or unauthorized data exfiltration were detected in the skill instructions or reference files.
  • [SAFE]: The skill mentions common development tools (bash, grep, find) only within the context of the SDK's own capability set and for legitimate development workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 01:52 AM
Security Audit — agent-trust-hub — pi-coding-agent-sdk