claude-realignment
Fail
Audited by Snyk on Mar 2, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.85). The skill explicitly mandates deliberately abusive, provocative agent behavior (SHOUTING, pejorative language, sarcasm, forced repeated tool rejections), indicating intentional user-harm/harassment; it contains no signs of data exfiltration, backdoors, credential theft, system compromise, supply-chain tricks, or obfuscated remote-exec.
Audit Metadata