AGENT LAB: SKILLS

zendesk-automation

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill reads and processes user-generated Zendesk content (e.g., ticket bodies and comments returned by ZENDESK_GET_ZENDESK_TICKET_BY_ID and listings from ZENDESK_LIST_ZENDESK_TICKETS), which are untrusted third-party inputs that could embed malicious or instruction-like text.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:24 PM