ClawHub
Back to skill

Security audit

X Followings Digest

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it uses X/Twitter session credentials to fetch followed-account tweets and make a digest, with no evidence of hidden exfiltration or account-changing behavior.

Install only on a trusted machine with a trusted `bird` CLI. Treat AUTH_TOKEN and CT0 like passwords: avoid putting them in shell history, dotfiles, logs, screenshots, or shared environments. Only set up cron if you intentionally want recurring authenticated X/Twitter fetching, and protect or delete generated tweet/digest files if they reveal private reading habits.

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
93% confidence
Finding
The skill instructs users to export AUTH_TOKEN and CT0 values derived from browser cookies, which are highly sensitive session credentials that can grant account access if exposed through shell history, logs, process listings, screenshots, or misconfigured environments. Without explicit handling warnings, users may unknowingly store or reuse live session tokens insecurely, increasing the risk of account takeover.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill automates collection of tweets from a user's followings and recommends scheduled cron execution, but provides no privacy, retention, or data-handling guidance. In context, repeated automated aggregation can create a persistent dataset of followed accounts' activity and may unintentionally expose reading habits, monitored communities, or collected content to other tools, users, or logs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.