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
进口税费核算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local import-duty worksheet checker that reads a user-provided file, performs deterministic arithmetic checks, and does not show network, persistence, credential, or destructive behavior.
Before installing, users should know this is a local Chinese-oriented worksheet checker, not customs or tax advice. It should be used with copied table text or JSON input, and users should review the listed checks that the free version does not perform.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (7)
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
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The manifest text says '触发词包括' and lists phrases such as '关税算错' and especially '完税价格', which are not clearly bounded as invocation commands and could appear in ordinary discussion of import paperwork. The description does not provide negative examples or contextual constraints to clarify when the skill should or should not activate.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This code file contains extensive natural-language instructions, contract details, and limitations entirely in Chinese, and later returns Chinese-only user-facing messages. That imposes a specific language on users without offering a locale choice or documenting a justified region-specific constraint.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The user-facing description, help text, and runtime messages are entirely in Chinese and present the skill as operating only through Chinese-language instructions and inputs, with no opt-in or alternative locale mentioned. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is explicitly justified.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The comment states that non-JSON input will be handled as plain-text material such as a '合同全文', which broadens the documented input scope beyond the manifest's stated purpose of checking an import-duty calculation table line by line. The actual CLI help and behavior elsewhere consistently expect a tax calculation table with headers, so this inline documentation is misleading about intended use.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The JSON contains only Chinese-language table content, which implies a fixed language/locale presentation. Under the policy rule, forcing a specific language without opt-in or documented regional justification is a natural-language policy concern.
- Content