Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
医疗器械UDI与出入库追溯核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language medical-device ledger checker that reads user-provided table text or JSON and reports deterministic issues without network, credential use, installation steps, or persistence.
Use this only on intended medical-device traceability ledgers, preferably with local copies you are allowed to process. The tool runs locally, but the ledgers may contain sensitive inventory or patient-destination information, and its output should not be treated as a final medical, quality, or legal compliance determination.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
- The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- This file’s natural-language interface is entirely Chinese, including the contract description, field labels, advice text, and output messages, with no indication that users can select another language. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern unless the locale restriction is clearly justified.
Natural-Language Policy Violations
Medium
- Confidence
- 90% confidence
- Finding
- The file's user-facing help, status messages, and operational descriptions are entirely in Chinese, with no indication that the user can choose another language or that the tool is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 89% confidence
- Finding
- L075 的注释写明“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，但本文件其他位置反复声明该工具只用于医疗器械 UDI 与出入库追溯材料核对。这里的“合同全文”示例会积极误导使用者对技能适用范围的理解，构成文档意图与技能实际目的的矛盾。
Natural-Language Policy Violations
Low
- Confidence
- 92% confidence
- Finding
- The JSON content is entirely in Chinese field labels and sample values, with no indication that language selection is optional or that the skill is region-specific. Under the policy, fixed locale/language behavior without user opt-in can be a natural-language policy concern.
Static analysis
No suspicious patterns detected.