consensus
Warn
Audited by Socket on Oct 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The research purpose is legitimate, but the skill’s actual footprint is not aligned with Consensus’s documented integration path: it rejects the official MCP/API flow and requires an unverifiable local binary that operates through a signed-in browser CDP session. That creates high install-trust and credential/session-forwarding risk even without direct evidence of malware.
Confidence: 90%Severity: 82%
Audit Metadata