claude-code-conventions

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a canonical reference for developers and agents. It documents JSON schemas (plugin.json, hooks.json, .mcp.json), frontmatter conventions, and file structures specific to the Claude Code platform.
  • [SAFE]: No obfuscation, data exfiltration, or prompt injection patterns were detected. All described paths (e.g., ~/.claude/settings.json) and variables (e.g., ${CLAUDE_PLUGIN_ROOT}) are standard configuration references for the platform's ecosystem.
  • [SAFE]: While the document describes how the platform executes hooks and commands, the skill itself does not perform any of these actions or provide instructions for unauthorized execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 10:45 AM
Security Audit — agent-trust-hub — claude-code-conventions