visa-vulnerability-agentic-harness
Warn
Audited by Socket on Oct 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is internally coherent and the documented install path looks same-org and benign, but its actual capability is an AI-driven security/exploit research harness. The main risk is not hidden malware behavior; it is the high-risk offensive scanning scope, external LLM data flow, optional custom gateways, and transitive agent-install behavior.
Confidence: 89%Severity: 74%
Audit Metadata