ClawHub
Back to skill

Security audit

Insurance Group Renewal

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only group insurance renewal guidance skill with clear data-minimization warnings and no code, tools, persistence, or hidden access.

Before installing, treat it as advisory insurance workflow material, not a substitute for actuarial, underwriting, legal, or compliance review. Avoid entering employee rosters, ID numbers, medical records, or identifiable claims details, and verify any regulatory or market claims against official sources before using them in real renewal decisions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list is very broad and includes generic terms like corporate insurance, employee benefits, HR welfare plans, and insurance procurement, which can match ordinary business conversations well beyond the skill’s intended scope. This can cause unintended invocation and context capture, increasing the chance that users are routed into specialized insurance guidance without clear intent, especially in mixed HR/benefits workflows where sensitive aggregate claims or benefits data may be discussed.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The description states the skill is built for China insurance use cases and mixes Chinese-role targeting, while the trigger section later marks Chinese trigger words as "优先". Although bilingual content is present elsewhere, the file does not explicitly tell users they may choose their preferred output language, which can be a locale/language policy concern.

Static analysis

No suspicious patterns detected.