ClawHub
Back to skill

Security audit

Bird Chrome

Security checks across malware telemetry and agentic risk

Overview

The skill’s X/Twitter automation is disclosed, but it gives an agent sensitive session access and public posting ability without enough per-action guardrails.

Install only if you are comfortable letting an agent use your logged-in X/Twitter session. Prefer a dedicated browser profile or test account, keep use read-only by default, do not share raw session tokens unless absolutely necessary, and require explicit confirmation of the exact post or reply before anything is submitted.

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
91% confidence
Finding
The skill instructs the agent to control the host browser and perform posting actions on a live X/Twitter account, including enabling host browser access, but it does not require an explicit user-facing confirmation about account, privacy, or side-effect risks at the point of action. In an agent setting, this increases the chance of unintended posts, interaction with the wrong account/profile, or exposure of session context through host-browser control.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal