skipfish
Warn
Audited by Socket on Oct 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is internally consistent and uses mostly legitimate package-manager install paths, with benign pre-execution checks. However, its core purpose is to give an AI agent offensive web-scanning capability, including authenticated scanning with user credentials, which makes it high-risk despite limited evidence of malware or exfiltration.
Confidence: 92%Severity: 78%
Audit Metadata