hunt-saml
Warn
Audited by Socket on Aug 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS/HIGH-RISK skill. Its contents are internally consistent with SAML security testing, but the skill is explicitly an offensive exploitation playbook for an AI agent, enabling account takeover and XXE against real systems. No clear malware or credential-harvesting behavior is present, but the exploit-focused functionality makes the skill dangerous.
Confidence: 91%Severity: 81%
Audit Metadata