ClawHub
Back to skill

Security audit

金匮要略智慧

Security checks for vulnerabilities and agentic risk

Overview

This is a static educational Chinese medicine methodology skill with no code execution, persistence, network access, or hidden agent-control behavior, though users should not treat it as medical advice.

Install only if you want historical or conceptual Chinese medicine reference material. Do not use it to diagnose symptoms, choose herbs or formulas, manage pregnancy-related issues, or delay urgent care; consult a qualified clinician for health 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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This skill contains extensive medical diagnostic and treatment content, including disease classification, treatment principles, and named formulas, but does not clearly warn users that it is educational only and not a substitute for licensed medical advice, diagnosis, or emergency care. Because the content is framed as actionable methodology and includes treatment-oriented guidance, users could over-rely on it for real health decisions, leading to delayed care or inappropriate self-treatment.

Content

No source excerpt is available for this finding.