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
税收优惠适用条件自查核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language tax self-check table validator that reads user-provided input and does not show evidence of network access, persistence, credential use, or hidden side effects.
Install only if you want a Chinese-language, local Node-based checker for this specific tax self-check table format. Treat its output as table arithmetic/reconciliation help, not tax or legal advice, and only point it at files you intend the local tool to read.
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
- 92% confidence
- Finding
The user-facing comments and operational description are entirely in Chinese, including warnings, scope, and usage expectations, with no indication that other languages are supported or that Chinese is optional. This creates a natural-language locale constraint that is not presented as opt-in or justified as a region-specific language requirement.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The user-facing description, usage text, prompts, and outputs are entirely in Chinese, indicating the skill is effectively constrained to a specific language. The file does not provide any opt-in, fallback, or documented justification for this locale restriction, which matches the language/locale policy violation category.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The inline comment at L075 gives the example 'directly pasted full contract text' (合同全文), which contradicts the rest of the file's stated intent: the tool expects a 税收优惠适用条件自查表 with headers and reports insufficient input when such structure is missing. This is not just incomplete documentation; it actively suggests a different document type than the code and user guidance support.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON text content is entirely in Chinese and does not indicate that the user can choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
- Content