ClawHub
Back to skill

Security audit

小红书面经采集与回答

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Windows-focused research helper that collects public RedNote interview posts and creates local interview-prep documents, with substantial but purpose-aligned setup requirements.

Before installing, understand that this skill sets up a local Windows runtime and uses Chrome/OpenCLI with your logged-in RedNote session to read public posts and download images. Use it only if you are comfortable approving those installs and keeping the generated local archive, resume-derived evidence index, and answer drafts on your machine.

SkillSpector

By NVIDIA
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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to perform file reads/writes, network access, and invoke local scripts and PowerShell, but the skill metadata shown does not declare any permissions. This mismatch weakens security review and user consent because the skill’s effective capabilities are broader than its declared interface, increasing the risk of unexpected local filesystem or network actions during execution.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Static analysis

No suspicious patterns detected.