Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
电商退货退款与库存回冲核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, deterministic checker for Chinese e-commerce return/refund spreadsheets and does not show hidden network, credential, persistence, or destructive behavior.
Install this only if you are comfortable running a local Node-based checker over copied return/refund spreadsheet data. Review the Chinese-language scope and required columns first; it does not connect to e-commerce, ERP, or inventory systems and does not provide legal, tax, audit, or refund-policy judgments.
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 (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The file’s natural-language comments and user-facing guidance are entirely in Chinese, including the usage description and input advice. There is no indication that language choice is optional or that the skill is region-specific, which can violate a language/locale policy requiring user choice or explicit justification.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The user-facing docstring, usage text, errors, and output strings are entirely in Chinese, and the file does not indicate that language choice is optional or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 84% confidence
- Finding
- L075 的注释称非 JSON 输入会被当作“例如直接粘贴的合同全文”处理，但该技能清单和其余帮助文本都限定为退货退款与库存回冲明细表核对。这不是代码越权执行，但文档示例主动暗示了与技能目的不符的输入范围，造成意图层面的误导。
Natural-Language Policy Violations
Low
- Confidence
- 94% confidence
- Finding
- The JSON sample text is entirely in Chinese, including headers and status values, which indicates a fixed language/locale assumption in the skill artifact. For an all-file-types policy check, this can be a natural-language locale constraint when no user opt-in or justification is provided.
Static analysis
No suspicious patterns detected.