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
审计调整分录核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local audit-adjustment table checker that reads user-provided input and does not show evidence of network use, credential access, persistence, or hidden behavior.
Install only if you are comfortable running a local Node.js checker on audit adjustment table text. Keep sensitive finance data local, review the Chinese-only output carefully, and do not treat the results as accounting advice because the skill explicitly checks only internal arithmetic and table consistency.
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 (5)
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
- 96% confidence
- Finding
This JavaScript file contains natural-language documentation and user-facing result text entirely in Chinese, including instructions, warnings, and output messages. Because the skill does not offer any language or locale choice or document a justified region-specific limitation, it imposes a specific language on users, which matches the locale-policy violation criteria.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The user-facing docstring, usage text, errors, and output strings are entirely in Chinese, which imposes a specific language/locale on users. The file does not indicate that language selection is optional or configurable, and no region-specific justification is provided.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% 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）”，但该脚本其余说明与错误提示均明确要求输入为“审计调整分录核对表（含表头）”。这不是单纯信息不全，而是举了一个与技能意图明显不一致的材料类型示例，容易误导调用方对技能适用范围的理解。
- Content