principles

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of natural language instructions and configuration metadata. It does not contain any executable scripts, binaries, or remote code patterns.
  • [SAFE]: The workflow relies on local skill discovery and reading frontmatter from existing /principle-* skills on the host's filesystem. It does not perform any network operations, exfiltration, or access to sensitive system directories (e.g., .ssh, .aws).
  • [SAFE]: The instructions establish clear composition boundaries, restricting the agent to the user's accepted requirements and action grants. It explicitly forbids principles from authorizing external publication or larger features.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill follows standard documentation and orchestration practices for AI agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 05:45 PM