ClawHub
Back to skill

Security audit

Webpack Config Validator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local webpack JSON config checker with no evidence of hidden data access, persistence, network use, or destructive behavior.

Install only if you want a local CLI-style validator for JSON-exported webpack configs. Run the Node export command only in projects you trust, because loading a webpack.config.js can execute code from that project; the validator script itself only reads the JSON file you pass and prints findings.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
78% confidence
Finding

The skill instructs users to run a validator against arbitrary JSON config files and explicitly references reading local files, but it does not declare any tool scope such as allowed-tools or permissions. In an agent environment, missing scope boundaries can cause the skill to inherit broader file-read capabilities than intended, increasing the risk of unauthorized access to local files if the input path is attacker-controlled or the skill is invoked in a sensitive workspace.

Content

No source excerpt is available for this finding.