zendesk-automation
Warn
Audited by Socket on Sep 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s Zendesk capabilities fit its stated purpose, but its actual trust and data flow model is problematic: it sends Zendesk operations and likely auth context through a third-party MCP intermediary, and the documented endpoint is outdated/discontinued relative to current official Composio infrastructure. This is not confirmed malware, but it is a high-risk integration pattern with meaningful trust and autonomy concerns.
Confidence: 88%Severity: 78%
Audit Metadata