xpull

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  1.0.1

Overview

This skill does what it says: it fetches X/Twitter content through disclosed external APIs, with a small local state file for call limits.

Before installing, be aware that tweet URLs and search queries are sent to api.fxtwitter.com or api.x.ai, and Grok usage requires an xAI API key and may incur costs. The skill also creates a small local .grok-state.json file to track daily Grok calls.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill explicitly states it sends data to third-party services (`api.fxtwitter.com` and `api.x.ai`) but does not provide a clear user-facing privacy warning about what input content, URLs, queries, or metadata will be transmitted externally. In an agent setting, users may assume local-only processing, so this omission can lead to unintended disclosure of sensitive links, search terms, or conversation context.

Missing User Warnings

Low

• Confidence: 84% confidence
• Finding: The skill notes that `grok-x-search.mjs` writes `.grok-state.json` next to the script, but it does not clearly warn users that running the skill creates a persistent local file. Undisclosed disk writes can surprise users, leak usage patterns, or create operational issues in read-only or sensitive environments.

VirusTotal

45/45 vendors flagged this skill as clean.