Skills
skills/kortix-ai/suna/claude-code/Gen Agent Trust Hub

claude-code

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill describes standard usage of the official Anthropic Claude Code CLI.
  • [COMMAND_EXECUTION]: Provides templates for executing shell commands via the claude -p interface to perform coding and analysis tasks.
  • [SAFE]: Includes a "supervision loop" that mandates independent verification of the sub-agent's output (reading files, re-running tests), preventing reliance on potentially incorrect self-reports.
  • [SAFE]: Recommends using the least privilege for permission modes (e.g., plan or default) and provides appropriate warnings for autonomous execution modes like bypassPermissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:57 PM
Security Audit — agent-trust-hub — claude-code