ClawHub
Back to skill

Security audit

Insurance Knowledge Qa

Security checks for vulnerabilities and agentic risk

Overview

This is a static insurance education skill with some broad triggers, but no hidden execution, persistence, or data-handling behavior.

Use this as general insurance education for China-market questions. Do not rely on it as legal, financial, or sales advice, and avoid sharing unnecessary health or financial details; verify policy-specific answers against the contract, insurer, regulator, or a qualified professional.

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)

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The description states the skill is "Built for China insurance consumers and professionals," which creates a locale-specific constraint in natural language. While a regional focus may be appropriate, the file does not clearly present this as an explicit opt-in choice or explain activation boundaries for non-China users.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes generic phrases such as "怎么选", "哪个好", and "是什么意思", which are common in ordinary conversation and can cause the skill to activate outside clearly insurance-related contexts. Unintended invocation can route unrelated user queries into this domain-specific skill, increasing the chance of confusing responses, privacy over-collection, or bypass of more appropriate skills.

Static analysis

No suspicious patterns detected.