Security audit

黄帝内经

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese medicine wellness skill with no executable behavior, but it gives diagnosis-like and treatment-style health guidance without clear medical safety limits.

Review carefully before installing. The package does not appear to run code or access your data, but its health content should be treated as cultural or educational wellness material, not diagnosis or treatment. Do not use its formula, herb, symptom, diet, or exercise guidance as a substitute for a qualified clinician, especially for symptoms, pregnancy, chronic conditions, medications, or urgent health concerns.

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)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill includes structured health assessment, diagnosis-like categorization, and treatment/guidance workflows but does not warn users that the content is educational, not medical advice, and not a substitute for professional care. In a health context, users may rely on these outputs for self-diagnosis, delaying appropriate medical evaluation or following unsuitable recommendations based on non-evidence-based frameworks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list includes very broad, everyday topics such as health, lifestyle, work-life balance, and mental well-being, which can cause the skill to activate in contexts where users did not specifically request traditional Chinese medicine guidance. Because the skill provides prescriptive health-related frameworks, accidental invocation can steer users toward quasi-medical recommendations without clear intent or informed consent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The file gives users diagnostic heuristics, syndrome differentiation steps, and concrete treatment recommendations including named formulas and medicinal ingredients, but it does not clearly state that this is educational content rather than medical advice or that users should seek qualified medical evaluation. In a health/wellness skill, users may rely on this material for self-diagnosis or self-treatment, which can delay appropriate care, worsen underlying disease, or lead to unsafe use of herbal products and contraindicated treatments.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This file provides detailed, prescriptive diet, exercise, sleep, and herbal/food guidance framed as health advice, but it does not include a safety disclaimer, contraindications, or direction to seek professional medical care. In a health/wellness skill, users may treat this as actionable medical guidance, which can delay appropriate treatment or cause harm for people with chronic disease, pregnancy, allergies, heat sensitivity, or other individualized risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: All user-facing content is presented only in Chinese, and the document does not indicate that the language is optional, user-selected, or justified as a region-specific artifact. This can violate a language/locale policy when a skill or reference material forces a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.