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
连锁加盟门店结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local settlement-table checker that reads user-provided input, runs bundled Node.js code, and does not show evidence of network use, persistence, or hidden behavior.
Install only if you are comfortable running a local Node.js checker on copied settlement-table data. The skill does not appear to send data over the network, but it handles business financial information and only performs the free checks it explicitly lists, so do not treat it as legal, tax, contract, or full audit advice.
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 (4)
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
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The user-facing description, usage text, and runtime messages are entirely in Chinese, with no indication that another language can be selected. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 93% 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）”，但该脚本的 manifest、帮助文本和其余注释都将技能限定为处理连锁门店结算核对表。这里把“合同全文”作为输入示例，主动暗示了与技能目的不符的文档类型，属于文档意图与实际技能定位的矛盾。
- Content