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分摊表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
制造费用分摊与吸收核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local factory-overhead table checker whose code and instructions are coherent, disclosed, and proportionate to its stated purpose.
Install this only if you are comfortable using a Chinese-first local CLI checker and providing it exported or pasted manufacturing overhead allocation table text. It does not appear to send data over the network or persist anything, but users should still avoid giving it unrelated sensitive documents because the tool is only designed to parse this specific table format.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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（样例本身就是一张自洽的分摊表）
- 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分摊表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 88% confidence
- Finding
- The manifest prominently presents the skill name and primary description in Chinese, while the English content is secondary and incomplete relative to the main instructions. This can amount to a language/locale policy issue because the skill experience is effectively constrained to a specific language without explicit user opt-in or a clear statement that multiple languages are supported equally.
Natural-Language Policy Violations
Medium
- Confidence
- 98% confidence
- Finding
- The file’s natural-language instructions, comments, sample data, labels, user-facing advice, and output text are all written exclusively in Chinese, with no indication that another language is supported or that the user can choose a locale. This creates a language-policy issue because the skill effectively enforces a specific language for user interaction and results.
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- This code file contains user-facing natural-language strings entirely in Chinese and labels the capability in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Intent-Code Divergence
Low
- Confidence
- 96% confidence
- Finding
- L075 的注释写道“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，但该脚本整体能力、帮助文案和错误提示都明确限定为制造费用归集与分摊表核对。这里不是单纯信息不全，而是举了与技能意图不一致的材料类型示例，容易误导开发者或使用者对技能实际适用范围的理解。
Static analysis
No suspicious patterns detected.