Back to skill

Security audit

用于自动扫描 Vue2 项目的潜在风险,依赖安全,Webpack 配置风险, Babel 配置问题

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Vue2 project risk checker that reads local project files and runs npm audit, with no hidden persistence or destructive behavior found.

Before installing, understand that this is a lightweight helper, not a full Vue2 security audit. It reads local project configuration and package data and may run npm audit against the npm registry; review the results manually and use broader security tooling for CI gating.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The skill advertises broad Vue2 risk scanning coverage, including Webpack and Babel configuration analysis, but the described behavior and static finding indicate those checks are not actually implemented. This can create a false sense of security in CI or developer workflows, causing users to rely on incomplete results and miss real security issues in the unscanned areas.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The script includes natural-language comments in Chinese (for example, '检查') without indicating that the skill is intentionally localized or limited to Chinese-speaking users. This can violate language/locale policy when a skill implicitly forces one language in its user-visible or maintainer-facing instructions without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The script includes natural-language comments in Chinese (e.g. '检查') without offering any language choice or documenting a locale-specific requirement. This can violate a language/locale policy when organizational standards require user-facing or maintainable skill content to avoid forcing a specific language by default.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/checks/check-webpack.sh:13