Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
药品耗材进销存与科室领用核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language checker for hospital supply inventory tables and its behavior matches that stated purpose.
Install only if you need a Chinese-language, local checker for hospital drug/supply inventory and department requisition tables. It does not send data over the network, but you should still review the generated findings yourself because it only checks table arithmetic and explicitly omits several paid-tier/business-policy checks.
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
Vulnerability Patterns
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (4)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file’s natural-language comments, labels, user-facing advice, and disclaimer are entirely written in Chinese, and the skill expects Chinese table headers and returns Chinese guidance. There is no indication that users may choose another language or locale, which can violate a language/locale policy requiring user choice or explicit justification.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The inline documentation says non-JSON input will be treated as plain-text material such as a '合同全文' (full contract text). That contradicts this skill's stated purpose and surrounding help text, which consistently describe only hospital drug/supply inventory-vs-department requisition table checking with headers.
- Content