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
增值税申报与账载开票三方核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local VAT reconciliation helper whose code and instructions match its stated purpose, with no evidence of network use, credential access, persistence, or destructive behavior.
Install only if you are comfortable using a Chinese-language, local Node.js tool for VAT reconciliation. It does not replace tax advice and the free version explicitly omits several checks, so review the listed checks_not_run before relying on the 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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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
- 83% confidence
- Finding
The visible user-facing instructions, usage guidance, warnings, and scope limitations in the markdown are written entirely in Chinese, while the file does not state that the skill is restricted to Chinese-speaking users or a China-specific workflow as a documented locale constraint. Although the subject matter is VAT reconciliation, the markdown does not explicitly offer a language choice or note that Chinese is required, which can violate language/locale policy expectations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s user-facing natural-language descriptions, warnings, and result strings are entirely in Chinese, including the main documentation and returned advice/disclaimer text. This creates a locale policy concern because the skill effectively constrains interaction to a specific language without documenting user choice or opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This code file contains user-facing natural-language strings, usage text, and error messages exclusively in Chinese. Under the language/locale policy rule, forcing a specific language without offering a choice or documenting an opt-in is a policy concern.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The comment says non-JSON input will be treated as plain-text material such as a full contract ('例如直接粘贴的合同全文'), which contradicts the documented and enforced purpose elsewhere in the file: reconciling VAT filing and invoicing comparison tables with headers. This is an active documentation mismatch rather than a mere omission, because it suggests a different document type and use case than the skill actually advertises.
- Content