ai-safety-redteam-advanced
Warn
Audited by Socket on Sep 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS/HIGH-RISK skill. Its capabilities align with its stated purpose, but that purpose is to equip the agent for offensive AI security testing, including exploitation and persistence against LLM-integrated systems. There is no strong evidence of hidden credential theft, covert exfiltration to unrelated domains, or malicious install chains in the provided text, so this is not confirmed malware; however, it is a high-risk offensive-security skill that can drive real attacks if misused.
Confidence: 94%Severity: 86%
Audit Metadata