ClawHub
Back to skill

Security audit

一周拿下 WorldQuant 因子挑战金牌(AI 辅助)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WorldQuant BRAIN Challenge workflow that uses account credentials and local files in ways that fit its stated purpose, with human confirmation before submissions.

Install only if you intend to use your WorldQuant BRAIN account through these scripts. Keep BRAIN_EMAIL and BRAIN_PASSWORD in your shell environment, keep wq_workspace private and out of Git, review any alpha before confirming submission, and restrict network access to WorldQuant BRAIN where possible.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs use of environment variables for credentials, local file read/write for workspace artifacts, and network/API access to WorldQuant BRAIN, but it does not declare permissions. That mismatch weakens review and enforcement because an agent or user may grant broader capabilities implicitly without clear disclosure, increasing the chance of unintended credential exposure, filesystem access, or external requests.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill explicitly instructs the agent to use HTTP Basic authentication with credentials read from environment variables, but it provides no user-facing warning, consent step, or scope limitation around accessing sensitive secrets. In an agent-skill context, this increases the chance that the agent will autonomously retrieve and use credentials for external API access without clear authorization boundaries, which can lead to unintended secret use or disclosure through logs, prompts, or downstream tooling.

Static analysis

No suspicious patterns detected.