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
研发费用加计扣除归集核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local R&D expense table checker with no evidence of network use, persistence, credential handling, or hidden behavior.
Before installing, understand that this is a Chinese-language, local-only checker for copied R&D expense collection table text. It can help find arithmetic and table consistency issues, but it explicitly does not provide tax advice or check all paid-version items.
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 (4)
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
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The docstring says non-JSON input is treated as plain-text material such as a pasted '合同全文', which implies broader document types are acceptable. However, the manifest and the rest of this runner consistently describe the skill as checking R&D expense collection tables with headers, and insufficient-input messaging also requires that specific table format.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The only natural-language content in this manifest-like JSON file is entirely in Chinese, which indicates a fixed language/locale expectation with no opt-in or alternative. Under the policy rule for language or locale constraints, this is a potential violation because the file does not offer the user any language choice or explain why Chinese is required.
- Content