Back to skill

Security audit

Customer Support Autopilot

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only support triage skill that appears coherent and safe to install with normal care for sensitive customer tickets.

Install only in an approved support workflow. Agents should review drafts before sending, verify SLA/refund/billing statements against current policy, and avoid including unnecessary sensitive customer information in prompts.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.