ticket-triage

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION] (File: "SKILL.md", "references/ticket-triage-checklist.md"): This skill processes customer support tickets, which constitute untrusted external data. Malicious actors could embed instructions within a ticket to manipulate the agent's classification, summarization, or routing recommendations. The skill mitigates this risk with explicit safety rules prohibiting unauthorized changes and the collection of secrets, and it does not utilize high-risk tools like network access or arbitrary code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:22 PM