inbound-triggers-30
Warn
Audited by Socket on Jul 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s marketing/prospecting purpose is coherent, but it couples a mostly informational taxonomy with an unpinned `npx` install that fetches and executes a remote MCP package, then forwards an API key into that runtime. Data flows are broadly consistent with ColdIQ’s service, but install trust and credential forwarding make the skill medium-high risk rather than benign.
Confidence: 84%Severity: 78%
Audit Metadata