test-ui
Warn
Audited by Socket on Oct 7, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core UI-audit purpose mostly matches browsing, screenshotting, and reporting, but the skill’s footprint expands meaningfully through raw session-secret collection, broad delegated subagent/workflow execution, and unspecified tooling provenance. I found no confirmed malware, no pre-execution directives, and no explicit exfiltration endpoint, but the credential-handling and transitive-trust scope are disproportionate enough to classify it as suspicious rather than benign.
Confidence: 84%Severity: 74%
Audit Metadata