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
现金盘点差异核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local cash-count checking tool that reads user-provided table data and shows no network, persistence, credential, or unrelated behavior.
Install only if you are comfortable running a local Node-based checker on cash-count tables, especially Chinese-language tables with the expected headers. Treat outputs as arithmetic/table consistency checks, not audit, legal, or fraud conclusions.
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
The file’s natural-language comments, user-facing advice, labels, and sample input are entirely Chinese and instruct users to provide data using Chinese column names. There is no indication that the skill supports other languages or that Chinese-only operation is an intentional, documented regional constraint, which can violate the language/locale policy.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a 'directly pasted full contract'（例如直接粘贴的合同全文）, but this skill is consistently documented and manifested as a cash-count reconciliation tool requiring a cash inventory table with headers. That example actively suggests a different document type than the code's stated intent and user guidance.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The JSON value on L2 is entirely in Chinese and provides no indication that the skill is region-specific or that users can choose another language or locale. Under the policy, fixed language content without opt-in or justification can be a locale-policy violation.
- Content