ClawHub
Back to skill

Security audit

captcha-login-assistant

Security checks across malware telemetry and agentic risk

Overview

This skill openly automates CAPTCHA-protected logins and password submission, but it is too broadly scoped and lacks clear authorization and consent safeguards.

Review carefully before installing. Use only on systems you own or are explicitly authorized to automate, confirm each target URL and form submission manually, avoid bypassing site anti-automation rules, do not paste real passwords into reusable scripts, and delete any saved login screenshots after use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The example trigger phrase is broad enough to match ordinary user requests like 'help me login,' which can cause the skill to activate in contexts beyond the user's clear informed intent. In this skill, that is more dangerous because activation leads directly to handling credentials, CAPTCHA solving, and automated submission on potentially arbitrary sites.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill is designed to process highly sensitive data, including usernames, passwords, login-page screenshots, and CAPTCHA content, but it does not provide a clear user-facing warning or consent flow describing privacy and security risks. This is especially risky because screenshots may capture additional secrets or personal data, and credential handling plus browser automation can expose users to accidental disclosure, retention, or misuse.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:54