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
教培课消与预收学费核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language tuition and training-hour reconciliation checker that reads a user-provided table and does not show network use, persistence, or hidden privilege behavior.
Install only if you are comfortable using a Chinese-language local checker for tuition and class-hour reconciliation tables. It processes potentially sensitive student and payment data, but the inspected code keeps processing local and does not show network transmission or persistence. Users should still verify financial conclusions because the free version explicitly omits some checks and does not provide accounting or contract-law judgment.
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 node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file’s natural-language comments, prompts, error messages, and result text are entirely in Chinese, including user-facing strings such as insufficiency notices and disclaimers. Because the skill does not offer a language/locale option or explain that it is restricted to a Chinese-speaking or China-specific deployment context, this can violate the language/locale policy requirement.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The insufficient-input message explicitly asks the user to provide a table containing "合同课时单价". However, no role mapping, required-column definition, or check logic exists for that field anywhere in the implementation, so the inline guidance overstates what the code actually consumes.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The inline comment states that invalid JSON will be processed as plain-text material such as a '合同全文' (full contract text). That contradicts the documented purpose elsewhere in this file and the manifest, which consistently says the tool reconciles 教培课消与预收学费核对表 and requires table content with headers.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The JSON sample text is entirely in Chinese, including field headers and record values, with no indication that the skill supports other languages or that the locale is intentionally restricted. For a general sample template, this can constitute a language/locale policy issue because it implicitly fixes the output/input language without user opt-in.
- Content