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
车辆保险与保费摊销核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
The skill is a local, deterministic checker for user-supplied vehicle insurance amortization tables, with no evidence of network access, persistence, credential use, or hidden behavior.
This appears safe to install for its stated purpose. Use it only with tables you intend the local Node script to read, and review negative-amount findings carefully because one user-facing message may be internally inconsistent for cancellation or endorsement reversals.
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 (4)
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
- 95% confidence
- Finding
The file’s natural-language interface, instructions, and user-facing messages are entirely in Chinese, including required input guidance and output text. There is no indication that users may choose another language or that the locale restriction is explicitly documented as a justified region-specific constraint.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The code comment at L109-L113 explicitly says the free tier intentionally excludes negative checks on beginning/ending unamortized balances and treats negative premiumAdd as a valid way to represent cancellations/endorsements. However, the emitted finding text says '本期新增保费' should not be negative, then immediately says cancellation/endorsement reversals should be shown as a negative '本期新增保费', which is self-contradictory and misstates the actual intended behavior.
- Content