pentest-ai-agents
Warn
Audited by Socket on May 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS/HIGH-RISK skill. Its capabilities are purpose-aligned for offensive security, so this is not deceptive in scope, but it intentionally enables an AI agent to perform exploit planning, phishing, credential capture, payload generation, and post-exploitation actions with real-world consequences. The same-org installer appears legitimate yet uses unpinned curl|bash. Overall this is not confirmed malware, but it is a high-risk offensive-security skill that should be treated as dangerous.
Confidence: 92%Severity: 93%
Audit Metadata