ClawHub
Back to skill

Security audit

广东省病案统计管理系统SQL查询大师

Security checks for vulnerabilities and agentic risk

Overview

This is a SQL helper for hospital records, but it shows identifiable patient-data queries without clear privacy, authorization, or minimum-necessary safeguards.

Install only for authorized healthcare database work. Users should require de-identified or aggregated queries by default, avoid SELECT * on patient or interface tables, mask direct identifiers unless specifically approved, and use the skill only in approved environments with normal access controls and audit logging.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is centered on generating SQL against highly sensitive hospital and patient-record tables, including diagnoses, operations, medical record numbers, names, lending logs, and insurance-upload data, yet it provides no privacy, authorization, minimum-necessary-use, or de-identification guidance. In practice, this materially increases the chance that an agent or user will retrieve, expose, or over-share protected health information from production systems, especially because the examples encourage broad SELECT queries over identifiable records rather than privacy-preserving patterns.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets the skill language to "zh-CN", and the visible metadata is entirely Chinese, which suggests the skill is intended to operate in a fixed language/locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.