type-juggling
Warn
Audited by Socket on Apr 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: internally coherent and not a credential-stealing or supply-chain skill, but it equips an AI agent with offensive vulnerability-exploitation guidance for PHP auth and signature bypasses. Main risk is exploit-enablement, not malware or exfiltration.
Confidence: 92%Severity: 72%
Audit Metadata