pi-extensions

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes utility scripts (e.g., scripts/pi-skill-registry.ts) designed to manage extensions and skills. These scripts execute shell commands for directory creation, archive extraction using tar, and package installation via bun install.
  • [EXTERNAL_DOWNLOADS]: The package management utilities download content from the official NPM registry (registry.npmjs.org), which is a well-known and trusted service for JavaScript/TypeScript packages.
  • [SAFE]: Deterministic matches for destructive commands such as rm -rf / in PATTERNS.md and assets/examples/permission-gate.ts are part of documentation and code examples that teach developers how to implement security middleware to intercept and block malicious shell commands.
  • [SAFE]: The inclusion of eval() in guides/01-quickstart.md is explicitly presented as a simplified demonstration for educational purposes within a code comment and is not part of any automated execution logic within the skill itself.
  • [SAFE]: The skill manifest and directives are consistent with its stated purpose as a developer guide and reference library.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 09:13 AM
Security Audit — agent-trust-hub — pi-extensions