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
农产品收购发票与进项抵扣核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language tax table checker that runs a bundled Node script on user-supplied input and shows no hidden network, persistence, or destructive behavior.
Install only if you are comfortable running a local Node.js checker on Chinese agricultural purchase invoice deduction table data. It does not appear to send data out, but it is limited to the listed free checks and should not be treated as tax advice or a substitute for official guidance.
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
- 89% confidence
- Finding
This JavaScript file contains extensive user-facing natural-language comments and output strings entirely in Chinese, including the tool description and result messages, but it does not offer any language or locale choice. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s user-facing description, usage, prompts, and output strings are entirely in Chinese, and there is no indication that users may choose another language or that the locale restriction is an intentional, justified policy requirement. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The comment says non-JSON input is treated as plain-text material, giving '例如直接粘贴的合同全文' as an example. But this skill is documented and messaged throughout as operating on '农产品收购发票与进项抵扣核对表' with table headers, so mentioning full contract text contradicts the intended input type rather than merely omitting detail.
- Content