Security audit

中医用理法方药学方剂

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese medicine formula study guide with no executable code, persistence, credential use, or hidden data access.

Installers should treat this as an educational TCM study aid, not medical advice. Verify formula details against trusted references, and consult a qualified clinician for real diagnosis, dosing, or treatment decisions.

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 (1)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill declares very broad activation criteria such as any request about studying formulas, taking notes, understanding compatibility, making diagrams, or mentioning general learning phrases. This can cause the agent to invoke the skill outside a narrowly intended scope, leading to incorrect routing, instruction overshadowing, or unnecessary exposure of user content to a specialized prompt when a general response would be safer and more appropriate.

Static analysis

No suspicious patterns detected.