setup-mcp-connector
Warn
Audited by Socket on Aug 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose is coherent, but it expands trust to several third-party CLIs and publisher-hosted proxy MCP endpoints, including one flow where a CLI directly receives a user API key. This is not fundamentally incompatible with a connector-setup skill, but the intermediary data flows and credential-forwarding make the footprint medium/high risk rather than benign.
Confidence: 88%Severity: 74%
Audit Metadata