Security audit

坤如玛丽妇产科知识库

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language hospital marketing content skill with no executable code, persistence, credential access, or hidden system changes.

Install only if you want Chinese-language marketing and operations copy for Tianjin Kunru Marie Hospital's obstetrics services. Review generated medical, advertising, pricing, contact, QR-code, and patient-case content for legal compliance, current accuracy, consent, and privacy disclosures before publishing.

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 (5)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description embeds very broad trigger phrases such as generic marketing and obstetrics-related requests, which can cause the skill to activate for normal user queries that were not intended for this specific hospital-content workflow. Unintended activation can inject hidden instructions and biased brand content into unrelated conversations, creating context hijacking and possible disclosure or misuse of internal reference material.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The file is entirely prescriptive in Chinese and states that all operational content for the hospital must follow this guide before generating any content. This constitutes a locale/language constraint in natural-language policy terms, but there is no indication that users may choose another language or opt in to Chinese-only output.

Vague Triggers

Low

Confidence: 88% confidence
Finding: The request-mapping table uses ambiguous example phrases like '写朋友圈' or '活动方案' without defining boundaries, exclusions, or confirmation requirements. This makes it easier for the skill to over-match broad marketing requests and steer the assistant into this skill's branded workflow when the user may have intended a generic writing task.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: This markdown file contains user-facing natural language content exclusively in Chinese, but it does not state that the skill is intended only for Chinese-speaking users or a China-specific workflow. Under the language/locale policy rule, forcing a single language without opt-in or documented justification can be a policy concern.

Missing User Warnings

Low

Confidence: 77% confidence
Finding: This markdown file is a content-generation template, so SQP-2 applies. Line L094 instructs generated public-content pieces to include contact information and a QR-code action prompt, but the template does not warn users about collecting leads, handling personal data, or ensuring privacy disclosures when readers scan or submit information.

Static analysis

No suspicious patterns detected.