ClawHub
Back to skill

Security audit

Cx Agent Studio

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for building CX Agent Studio agents, with no hidden code, install hooks, or automatic access to user data.

Before using the guidance to build real customer-facing agents, review any CX Agent Studio tools, callbacks, SaaS connectors, logging, and data-store settings you configure, because those product features can handle sensitive data even though this skill itself only provides documentation.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Findings (1)

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The text says 'Design agents in English,' which imposes a specific language requirement in the skill instructions. Although it also says agents respond in the end-user's language, the authoring requirement still reflects a language policy constraint without clear opt-in or justification.

Static analysis

No suspicious patterns detected.