connect
Warn
Audited by Socket on May 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's purpose is coherent, but its trust boundary is too vague: it relies on an undisclosed local script, unnamed npx connector packages, and a fallback to custom/npm-discovered MCP servers. That makes install trust and credential forwarding hard to verify, especially for API keys supplied to third-party connector code.
Confidence: 84%Severity: 72%
Audit Metadata