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
广告代理返点与框架返点核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese-language rebate table checker that reads user-provided input and reports calculation issues without network use, persistence, or data mutation.
Install only if you are comfortable using a Chinese-language local checker for rebate reconciliation tables. It does not appear to send data out or modify files, but users should understand the free version omits several checks that it lists separately in its output.
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 (8)
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
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
L11 的技能描述明确把“重复与空缺检测”列为免费版能力的一部分，L29 也再次声明会做“重复与空缺检测”。但 L68 在“本版本不包含”列表中又写明“不包含同一媒体重复计返点提示”，这对是否检测重复项形成了直接文档级矛盾，容易误导用户对免费版实际能力的预期。
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s descriptive comments and all user-facing messages are written exclusively in Chinese, and the skill does not indicate any option for the user to choose another language. Under the stated 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
- 78% confidence
- Finding
The skill claims '完全本地运行' and 'no network', but it also permits Bash, which can invoke arbitrary system utilities including network-capable commands. That mismatch can mislead users and downstream policy engines into trusting the skill as offline-only when the declared tool surface still allows data exfiltration or remote fetches if the implementation or future edits use shell access unsafely.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
This code file contains natural-language strings and documentation entirely in Chinese, including usage, errors, and result messaging. Under the policy rule, forcing a specific language without user choice can be a locale/language policy violation when no opt-in or alternative is provided.
- 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）”，但本技能其余文档与交互文案都强调输入应为“广告代理返点与框架返点核对表（含表头）”。这会对开发者意图造成误导：注释暗示适用更宽泛的合同类材料，而代码与技能定位实际都围绕返点核对表展开。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The only natural-language content in this file is a Chinese table header and dataset, with no indication that language selection is optional or that the skill is region-specific. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.
- Content