Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例（一张干净台账，应报 0 条问题）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
电梯维保与年检记录核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, disclosed checker for elevator maintenance records and does not show hidden network, credential, persistence, or destructive behavior.
Install only if you are comfortable running a local Node-based checker on elevator maintenance ledger text. The tool is Chinese-oriented and advisory: it checks the ledger text only, does not verify original PDFs/XLSX files or regulatory databases, and should not be treated as proof of real-world compliance.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (8)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例（一张干净台账，应报 0 条问题）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例（一张干净台账，应报 0 条问题）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
- The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file’s natural-language description, required input advice, error messages, and result text are all hard-coded in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The file's user-facing description, usage, errors, and output strings are entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 89% confidence
- Finding
- The comment says non-JSON input will be treated as plain-text material such as '直接粘贴的合同全文', but the rest of the file consistently describes the accepted material as elevator maintenance/inspection records with headers. This is an active documentation contradiction rather than mere incompleteness, because it suggests a different document type than the skill is designed to process.
Natural-Language Policy Violations
Low
- Confidence
- 82% confidence
- Finding
- The JSON text payload consists entirely of Chinese field labels and records, with no indication that language selection is optional or that the file is intentionally limited to a Chinese-only regional workflow. Under the language/locale policy check, this can be considered a natural-language locale constraint presented without explicit opt-in or justification.
Static analysis
No suspicious patterns detected.