Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项（以引擎的 `CHECKS_*` 导出为准）。
Security audit
残疾人就业保障金申报核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local worksheet-checking tool whose code and permissions match its stated disability employment fund review purpose.
Install only if you want a local Chinese-language checker for disability employment fund worksheet arithmetic. It does not contact the network or modify files, but it is not tax advice and it does not verify local policy parameters, certificates, contracts, or XLSX files; provide only the worksheet text needed for the check.
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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项（以引擎的 `CHECKS_*` 导出为准）。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项（以引擎的 `CHECKS_*` 导出为准）。
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
User-visible strings throughout the skill, including comments describing the contract, error advice, findings, summaries, and notes, are written in Chinese only. This creates a locale policy concern because the skill does not appear to offer any user opt-in or alternative language selection.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The user-facing description, help text, errors, and usage guidance 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 China-specific user base. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 88% 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）”，这与文件其余位置反复声明的残保金申报表专用用途不一致。代码确实会接受任意纯文本，但该注释用“合同全文”举例，主动传达了超出本技能定位的适用对象，构成文档意图与技能实际定位的偏离。
- Content