web-saml
Warn
Audited by Socket on Sep 20, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally coherent as an offensive SAML-auth attack technique, but it gives an AI agent explicit exploit guidance for authentication bypass and account impersonation. Install trust is relatively low-risk because no installer commands or credential forwarding are present, yet the capability itself is high-risk and disproportionate for general use.
Confidence: 92%Severity: 81%
Audit Metadata