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
应收账款账龄核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local AR aging table checker whose scripts match the stated purpose and do not show network use, persistence, credential access, or data mutation.
Install only if you are comfortable running a local Node-based checker on receivables tables and with Chinese-language output. The inspected package does not send data over the network, but the table contents may contain sensitive business information, so provide only files you intend the local tool to read.
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
- 97% confidence
- Finding
The file’s user-facing natural-language comments and output strings are written entirely in Chinese, indicating the skill is designed to communicate in a single language. There is no visible opt-in, locale selection, or justification that this is a region-specific tool, so this appears to violate the language/locale policy requirement.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The JSON sample consists entirely of Chinese column headers and customer labels, indicating a fixed language/locale with no accompanying opt-in, alternative locale, or justification. Under the policy, hard-coded locale constraints should be flagged unless the file clearly offers language choice or documents a region-specific reason.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The inline documentation says non-JSON input will be handled as '纯文本材料（例如直接粘贴的合同全文）', which contradicts the surrounding manifest and usage text that repeatedly require an AR reconciliation/aging table with headers. The code itself passes arbitrary text through to the engine, but the comment's contract-text example conflicts with the declared skill intent and could mislead developers about acceptable scope.
- Content