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
库存账实核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local inventory reconciliation checker that reads a user-provided table and does not show network, persistence, credential, or hidden mutation behavior.
Install only if you are comfortable using a Chinese-language local inventory reconciliation tool. It processes the input file you point it at, so avoid passing unrelated sensitive documents; the reviewed code does not send data over the network or persist results.
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
- 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
- 95% confidence
- Finding
This JavaScript file's natural-language interface is entirely Chinese, including the main file description, input requirements, and operational notes. The skill does not offer any language choice or document that it is intentionally limited to a Chinese-speaking/regional context, which can violate locale/language policy requirements.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The insufficient-input responses are emitted only in Chinese, which forces a specific language on users of the skill. Because there is no opt-in or fallback locale behavior, this constitutes a natural-language policy concern rather than a code-security issue.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The result payload contains Chinese-only summary text and notes, including basis explanations and pass/fail commentary. This enforces a single language for outputs without offering users a choice or stating a justified locale restriction.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- 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）”，但该脚本整体用途、帮助信息和后续提示都明确限定为库存盘点表核对。这里的文档示例主动暗示可处理合同，与代码和技能声明的库存盘点表场景相矛盾，属于意图层面的文档偏差。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The JSON template hard-codes all field labels and sample data in Chinese, which indicates a fixed language/locale assumption. For a general-purpose skill artifact, this can violate language-choice policy when no user opt-in or justification for a China-specific locale is provided.
- Content