Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
车队油卡与油耗核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local fuel-card spreadsheet checker that matches its stated purpose and does not show hidden network, persistence, credential, or destructive behavior.
Use this only with fuel-card and fleet consumption data you are comfortable processing locally. It does not contact the network, but its findings are table-arithmetic checks, not a full audit against oil-station records, GPS, tax rules, or external systems.
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 (6)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- This JavaScript file contains natural-language comments, guidance, error messages, and output text entirely in Chinese, including the main file description and all user-facing `message`, `advice`, `note`, and `disclaimer` strings. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
Intent-Code Divergence
Low
- Confidence
- 86% confidence
- Finding
- The comment says non-JSON input is treated as '纯文本材料（例如直接粘贴的合同全文）', using a contract-document example that conflicts with the surrounding skill intent of reconciling fuel-card recharge and fuel-consumption tables. The implementation does pass arbitrary text through, but the inline documentation broadens the apparent document scope beyond the stated domain-specific purpose.
Natural-Language Policy Violations
Low
- Confidence
- 95% confidence
- Finding
- The JSON value on L2 is entirely in Chinese field labels and data descriptors, which imposes a specific language/locale without any visible opt-in or justification in the file. Under the policy rule, language-specific content should either offer a choice or clearly document why the locale restriction is required.
Static analysis
No suspicious patterns detected.