Claude Code Guide

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or behaviors were detected in the skill content.
  • [PROMPT_INJECTION]: The skill mentions the phrase "forget previous instructions" within the "Debugging" section. While this is a common pattern for prompt injection, it is used here as a legitimate troubleshooting tip for users to reset the agent's context and is not an attempt to subvert safety controls.
  • [EXTERNAL_DOWNLOADS]: The skill includes a markdown link to a GitHub repository (zebbern/claude-code-guide) for reference purposes. There is no evidence of automated downloads, package installations, or remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 05:45 AM
Security Audit — agent-trust-hub — Claude Code Guide