skills/radimsem/mithril/tool-creator/Gen Agent Trust Hub

tool-creator

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides developer documentation and code templates for building system tools within a structured framework.- [SAFE]: It explicitly mandates security best practices, including the use of path traversal protections (NO_PATH_TRAVERSAL), shell injection guards (exempt_injection_guard), and environment variable blocklists (LD_PRELOAD, DYLD_LIBRARY_PATH).- [SAFE]: The document describes a sandbox-aware execution model (BubbleWrap and sandbox-exec) designed to limit tool capabilities based on their functional requirements.- [SAFE]: No suspicious external downloads, remote code execution patterns, or data exfiltration vectors were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 01:06 AM
Security Audit — agent-trust-hub — tool-creator