Zendesk Automation
Warn
Audited by Socket on Oct 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
Purpose and described capabilities are coherent for a Zendesk support skill, but the trust boundary is the problem: the real execution path is an unspecified `helpdesk-mcp` server with no verifiable publisher, package, or release provenance. Because that component would handle sensitive support data and likely credentials while taking autonomous actions in Zendesk/Slack/JIRA, this skill is best classified as suspicious/high-risk rather than benign.
Confidence: 83%Severity: 82%
Audit Metadata