support-ticket-triage

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists of text-based instructions for a triage workflow.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (support tickets, emails, and chat transcripts), which represents a standard risk surface for indirect prompt injection. However, since the skill does not define any tool use, network access, or shell command execution, the risk is negligible.
  • Ingestion points: Ticket text (include attachments/links) in SKILL.md.
  • Boundary markers: Not present.
  • Capability inventory: No tools, subprocess calls, or network operations are configured or requested.
  • Sanitization: The skill recommends masking PII before sharing data externally, but does not specify sanitization for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:33 PM
Security Audit — agent-trust-hub — support-ticket-triage