hunt-shadow-api
Warn
Audited by Socket on Sep 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: internally coherent and not obviously credential-stealing, but it is an offensive red-team skill that enables active API security probing on real targets. Install/data-flow trust is relatively clean; the main risk is the agent capability itself—enumeration and behavioral testing of hidden API versions can cause unauthorized security testing if misused.
Confidence: 90%Severity: 78%
Audit Metadata