ClawHub
Back to skill

Security audit

X Articles

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed X article publishing helper, but it can act through a logged-in browser so users should review before posting.

Install only if you are comfortable letting an agent control a browser already logged into X. Review the account, article text, media, and final publish dialog yourself before posting, and keep the CDP browser local and limited to the account you intend to use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill provides end-to-end browser automation that navigates to X's article composer and executes a publish flow, including a final confirmation click, without requiring an explicit user approval step or warning immediately before the external posting action. In an agent context, this can cause unintended public publication from a logged-in social media account, creating reputational, operational, and content-integrity risk even if no credential theft or code execution is involved.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.