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
应付账款账龄与付款计划核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language accounting table checker that reads user-provided input and prints deterministic findings without network access, persistence, or data mutation.
Install only if you are comfortable using a Chinese-language local checker for AP aging/payment-plan tables. Review the listed checks that are not included in the free version before relying on a clean result for financial review.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (7)
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
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The documentation is internally inconsistent: the '常见错法' section says some conditions '会被报出来' or otherwise suggests these conditions are checked, while the later '需要完整档时' section states the free version does not include several of those same checks. This can mislead users about the skill's actual coverage, causing them to rely on missing validations in a financial review workflow and overlook real accounting anomalies.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This code returns a user-facing instruction entirely in Chinese, telling the user to paste a specific table format, while the file also contains Chinese-only labels and messages throughout. Under the policy rule, forcing a specific language without opt-in is a natural-language locale violation unless the constraint is explicitly justified or alternatives are offered.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This code file contains extensive user-facing natural-language strings, help text, and status messages exclusively in Chinese. The policy calls for flagging language or locale constraints when the skill forces a specific language without user opt-in, and this file provides no alternative language option or explicit justification for the restriction.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
L075 的注释写明“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，但该脚本其余说明和用法都强调输入应为“应付账款账龄与付款计划表（含表头）”。这不是单纯信息缺失，而是示例性文档把预期材料类型说成了另一类文档，容易误导调用方对技能意图的理解。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The JSON payload contains only Chinese headers and values with no indication that language choice is configurable or user-selected. Per the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.
- Content