input-sanitisation
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely defensive and educational in nature. It contains patterns for preventing injection attacks and provides detection rules using
rg(ripgrep) to help the agent find security vulnerabilities in user code. There are no indications of prompt injection, data exfiltration, or unauthorized command execution. All code examples for dangerous patterns are clearly labeled and intended for detection rather than execution.
Audit Metadata