subagent-engineering

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of instructional markdown files and configuration templates designed to guide subagent engineering; it contains no malicious scripts or automated execution triggers.
  • [SAFE]: The documentation explicitly promotes security best practices, such as restricting tool access to the minimum necessary permissions and using 'plan' mode for read-only agents.
  • [SAFE]: Mentions of high-privilege features like 'bypassPermissions' are accompanied by clear security warnings and guidance on proper usage in controlled environments.
  • [SAFE]: External URLs within the inventory file point exclusively to well-known technology blogs, official documentation, and reputable community repositories.
  • [SAFE]: The skill provides defensive code examples, such as hook scripts that validate and block destructive database commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 04:45 AM
Security Audit — agent-trust-hub — subagent-engineering