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
增值税加计抵减核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese VAT ledger checker with disclosed limits and no evidence of network use, persistence, credential access, or hidden behavior.
Install only if you need a Chinese-language local checker for VAT add-on deduction ledgers. It does not provide tax advice, policy eligibility decisions, e-tax system integration, or the withheld paid-tier checks, so users should review the listed scope before relying on results.
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 (5)
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 file’s natural-language instructions, warnings, labels, and user-facing messages are entirely in Chinese, and there is no indication that the skill supports user language choice or that Chinese-only behavior is an explicitly justified regional constraint. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The JSON text content is entirely in Chinese and provides no indication that language selection is optional or that the file is intended only for a Chinese-language or region-specific context. This can violate language or locale policy when a skill or template implicitly forces a specific language without user opt-in.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The inline comment says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which contradicts the rest of the file and manifest that scope the skill to 增值税加计抵减台账核对. The code and usage text expect VAT deduction ledger text with headers, not arbitrary contract text.
- Content