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
收款手续费核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local payment-fee worksheet checker that reads user-provided table data and does not show evidence of network use, persistence, credential access, or data mutation.
Install only if you are comfortable running a local Node script on payment-fee worksheet text. Because the activation phrases are broad and the content is financial, provide an explicit worksheet/table input and verify the reported calculations before relying on them for accounting decisions.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (6)
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
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger phrases are very broad business/accounting terms such as 手续费核对, 收款对账, 渠道费率, and 结算金额, which can appear in many ordinary finance conversations. Without tighter activation boundaries, the skill may be invoked unintentionally and process unrelated financial content, increasing the risk of inappropriate tool use or user confusion.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file’s natural-language comments and user-facing advice strings are entirely in Chinese and describe the tool contract and usage in that language only. This can violate a language/locale policy when a skill imposes a specific language without user opt-in or an explicitly documented regional justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The visible skill name, summary, and primary description are all in Chinese, and the usage and operational guidance in the document are likewise Chinese-first. Although there is an English description field, the skill does not state that users may choose their preferred language for interaction or output.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The inline comment states that non-JSON input will be treated as plain-text material such as '直接粘贴的合同全文', which contradicts the surrounding manifest and usage text that repeatedly require a 收款手续费核对表 with headers. The code does accept arbitrary plain text and passes it to the engine, but the documented example broadens intent beyond the declared table-checking scope.
- Content