ClawHub

Bird Twitter

Security checks across malware telemetry and agentic risk

Overview

This is a transparent Twitter/X CLI wrapper, but it asks for live session cookies and enables real account actions without enough safety warning.

Install only if you are comfortable giving the agent environment live Twitter/X session authority. Treat AUTH_TOKEN and CT0 like passwords: do not commit, log, share, or paste them into untrusted shells. Use explicit prompts for tweet, reply, follow, and unfollow actions, and revoke or refresh your Twitter/X session if the cookies may have been exposed.

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 (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill enables account-impacting actions such as posting tweets, following users, and reading private account-context data like home timeline, likes, bookmarks, and mentions, but does not clearly warn users that these actions can affect their account or expose personal data. In an agent context, this increases the risk of users invoking impactful commands without informed consent or understanding the privacy implications.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs users to extract raw `auth_token` and `ct0` browser cookies and place them into environment variables without warning that these are highly sensitive session credentials. If mishandled, logged, shared, or exposed to other tools, these tokens could allow unauthorized access to the user's Twitter/X account and enable posting, reading account data, or changing account state.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal