ClawHub
Back to skill

Security audit

X Twitter

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward X/Twitter API helper with read-oriented scripts, but users should handle the bearer token and saved output paths carefully.

Install only if you are comfortable giving it an X/Twitter bearer token and sending your searches, tweet IDs, and trend requests to X. Prefer a limited/read-only token, avoid storing it in synced shell startup files, rotate it if exposed, and use --save only with output paths you intentionally choose.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding
The skill claims support for OAuth 2.0 and article retrieval, but the described behavior only uses a bearer token and appears to treat article-style URLs as tweet IDs. This mismatch can mislead users into trusting unsupported authentication or data retrieval behavior, causing improper deployment decisions, broken access-control assumptions, or incorrect handling of content and credentials.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README instructs users to place a long-lived X bearer token in shell startup files such as ~/.bashrc or ~/.zshrc, which creates persistent credential exposure risk. Those files are often broadly readable to the local user, copied into backups, synced, inspected during troubleshooting, or accidentally committed, so documenting this pattern without any warning or safer alternative normalizes insecure secret handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal