ClawHub
Back to skill

Security audit

买重大疾病保险不踩雷 | Critical Illness Insurance Advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese insurance-advice skill that asks sensitive but relevant health and financial questions, with no code, persistence, or hidden execution.

Install only if you want a Chinese critical-illness insurance planning questionnaire. Do not share medical, family-history, income, or debt details you are not comfortable providing, and treat its output as informational rather than licensed insurance or medical advice.

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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly collects highly sensitive personal data, including health conditions, genetic/family disease history, lifestyle factors, and financial status, but does not present a prominent upfront warning and consent step before collection begins. This creates privacy and compliance risk because users may disclose sensitive data without understanding its sensitivity, purpose, handling, retention, or optionality.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill name, description, triggers, workflow, and user interaction are all specified only in Chinese, and there is no indication that users may choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale limitation is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad phrases such as '买保险' and '保险建议' that can match ordinary conversation unrelated to this specific skill. Over-broad activation can cause the agent to unexpectedly enter a sensitive insurance-advice workflow and begin soliciting personal or health-related information without clear user intent.

Content

No source excerpt is available for this finding.