ClawHub
Back to skill

Security audit

UNCLEMATTCONNECTTOGPTWEBLOGINOFFIREFORWEBGPTLOGINGTOYOURSHIT

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed bridge to an already logged-in local Codex/ChatGPT session and does not show credential theft, hidden persistence, or destructive behavior.

Install only if you intentionally want a skill that can use your already-authenticated local Codex/ChatGPT session. Do not send secrets, private documents, cookies, API keys, or regulated personal data through its ask or smoke commands unless you are comfortable sending that prompt content to the provider account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/gpt-web-login-bridge.js:28