ClawHub
Back to skill

Security audit

Insurance Private Domain Ops

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only insurance operations guidance skill with explicit limits against sending messages, exporting customer lists, or connecting to CRM/WeChat systems.

Before installing, treat the skill as advisory material for insurance marketing operations, not an automation connector. Do not paste real bulk customer identifiers into chat, and keep any outreach, AI calls, customer-list handling, and compliance review inside your approved company systems and local regulatory process.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file states '以中文为主' as a default language policy for the skill. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation unless a justified locale restriction is clearly documented; here the statement sets a language default but does not offer a user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.