Claude Code Guide

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's debugging section explicitly suggests that users ask the agent to 'forget previous instructions' if it becomes confused. This phrase is a common prompt injection technique designed to override the agent's system prompt and established safety or operational guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:13 AM