Back to skill

Security audit

保险保单分析助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese insurance-policy analysis assistant that asks for sensitive personal and policy details, but the requests are disclosed and aligned with its stated purpose.

Install only if you are comfortable using a Chinese-language insurance analysis helper and sharing sensitive health, family, financial, and policy information in the chat. Redact names, ID numbers, addresses, policy numbers, and other identifiers unless they are truly needed, and treat the output as informational rather than professional insurance advice.

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
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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to activate on many generic insurance-related conversations, which can cause the skill to engage when the user did not explicitly request policy analysis. In this skill, that increases the chance of unnecessary collection of sensitive personal and financial data such as age, health status, family structure, income, debt, and insurance details.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses only Chinese throughout the title, instructions, tables, and notes, which effectively forces a specific language for users of the skill. Under the policy, language constraints should either be optional for the user or clearly documented as justified for a region-specific tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This questionnaire requests a broad set of sensitive personal data, including health status, family details, income, debt, and insurance policy information, but provides no notice about why the data is collected, how it will be stored, who can access it, or how long it will be retained. In the context of an insurance-analysis skill, this data is highly sensitive and could enable privacy harm, profiling, or financial targeting if mishandled or exposed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill content, trigger phrases, workflow, and output templates all assume Chinese-language interaction, and there is no indication that users may choose another language. This can violate a language/locale policy when a skill forces one language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

A language or locale policy issue exists when a skill forces a specific language without user choice. This questionnaire is presented only in Chinese and contains no indication that users may choose another language or that the locale restriction is intentional and documented.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, with no indication that the user can choose another language or that the locale restriction is justified. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.