cs-ticket-triage

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard business logic for ticket classification and priority assessment. No malicious code patterns, prompt injections, or unauthorized network calls were detected during the analysis.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill documentation includes a mandatory requirement for the agent to mask sensitive personal information (PII), such as resident registration numbers and credit card details, which is a significant security control to prevent accidental data leakage.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of customer support inquiries, which is an inherent surface for indirect prompt injection.
  • Ingestion points: Customer support inquiries received via email, chat, SNS, and mobile applications as defined in SKILL.md.
  • Boundary markers: The provided instructions do not specify the use of delimiters or specific boundary markers for incoming user content.
  • Capability inventory: The skill's capabilities are restricted to classification, priority assignment, and cross-referencing other internal vendor-provided skills; it does not possess access to high-risk tools such as shell environments, persistent file systems, or external HTTP requests.
  • Sanitization: The skill mandates the masking of sensitive data fields to protect user privacy before further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — cs-ticket-triage