Security audit

Health Industry Specialist

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language health, beauty, CRM, and Douyin operations reference skill with sensitive business and customer-data topics, but no hidden code, persistence, or deceptive behavior was found.

Installers should treat this as business reference content, not a ready-to-run compliant CRM or medical system. Before using it with real customers, add consent records, opt-out handling, privacy notices, retention limits, access controls, image/testimonial permissions, and licensed professional review for health or postpartum/chronic-condition 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

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 (9)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The template explicitly collects sensitive personal and health-related data such as contact details, allergies, diseases, and service history, but it does not pair that collection with consent, purpose limitation, retention, minimization, or lawful-processing requirements. In a CRM context for health/beauty services, this creates a realistic privacy and compliance risk because operators could adopt the template as-is and begin processing special-category data without adequate user notice or authorization.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The reminder and follow-up workflows automate outbound customer contact on fixed schedules, but they do not require opt-in, channel-specific consent, frequency limits, unsubscribe handling, or suppression rules. This can lead to harassment, spam, or unlawful direct marketing, especially when integrated with messaging platforms like WeChat or Douyin and tied to sensitive health-related customer relationships.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The guide operationalizes collection of customer personal information during预约/支付流程 without presenting privacy notice, data-minimization rules, retention limits, or explicit consent requirements at the point of collection. In a marketing and local-services context, this can lead to over-collection, unauthorized reuse, or mishandling of identifiable customer data, creating privacy, legal, and trust risks.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The success-case templates encourage before/after displays and customer story sharing, but they do not require explicit, documented consent before publishing identifiable customer images, health/beauty outcomes, or testimonial content. Because this material may reveal sensitive appearance, health-adjacent, or personal status information, publishing it without clear authorization can cause privacy harm, reputational damage, and regulatory exposure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This document provides detailed weight-loss plans, caloric targets, exercise guidance, monitoring advice, and outcome examples, including references to postpartum recovery, 'three highs' conditions, medication assistance, and genetic/metabolic assessment, without a prominent medical disclaimer or clear instruction to consult qualified clinicians for people with underlying conditions. In a health-related skill, users may treat this as actionable advice and apply it inappropriately, which could lead to unsafe dieting, overexercise, delayed medical care, or harm to vulnerable populations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file presents all user-facing instructions and invocation examples exclusively in Chinese, but it does not state that the skill is intended only for Chinese-speaking users or offer a language choice. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: 文档中的模板、自动回复和客户触达文案全部固定为中文，没有说明可根据用户偏好切换语言或仅适用于中文场景。若该技能面向通用用户使用，这种未声明的单一语言约束可能构成语言/locale 政策问题。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 62% confidence
Finding: A natural-language policy concern can arise when a skill effectively assumes a single language without offering alternatives or noting that the locale is intentional. This document is entirely in Chinese and does not state that the content is region-specific or that language can be adapted for the user.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: All headings and instructions are written exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this locale. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.