zendesk-triage

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the composio CLI to discover tools, fetch schemas, and execute Zendesk API calls during the ticket triage process.- [PROMPT_INJECTION]: The skill ingests untrusted data from Zendesk tickets, creating a surface for indirect prompt injection.
  • Ingestion points: Ticket details and comments fetched in Step 4 of SKILL.md.
  • Boundary markers: Absent; ticket content is interpolated into the triage context without delimiters.
  • Capability inventory: Subprocess execution via composio for searching and fetching data.
  • Sanitization: Absent; ticket content is processed directly for priority and category classification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 04:22 PM
Security Audit — agent-trust-hub — zendesk-triage