X Profile Deep Dive

• Outcome: Review
• Latest audit: May 29, 2026 at 9:39 PM UTC
• Version:
  1.0.5

Overview

The skill appears useful for X/Twitter profile analysis, but it asks users to use Twitter/X session cookies and expands collection beyond X without enough safety boundaries.

Review this before installing. Use only a dedicated low-privilege Twitter/X account, treat cookies as passwords, never paste them into chats or commit them to files, and avoid running broad off-platform collection unless you explicitly want that data gathered and stored.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 88% confidence
• Finding: The skill's stated purpose is X/Twitter profile analysis, but it instructs browsing external blogs/newsletters and curating off-platform content. This scope expansion increases data collection beyond user expectations and can pull the agent into additional sites, tracking surfaces, and content retention behaviors not covered by the original task boundary.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README instructs users to install tweety-ns and provide Twitter/X authentication cookies, and describes collecting tweets, followers, and followings, but it does not warn about the sensitivity of authentication cookies or the privacy/compliance implications of collecting social-network data. In a skill specifically designed to profile third-party accounts, this omission can lead users to expose account credentials or perform data collection without informed consent or adequate safeguards.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill depends on Twitter cookies and session material and even instructs users to extract them via browser tooling, but it does not present a strong user-facing warning about handling authentication secrets. Cookies/session tokens are highly sensitive; improper storage, logging, or reuse could enable account takeover or unauthorized access to private account capabilities.

Missing User Warnings

Low

• Confidence: 80% confidence
• Finding: The skill directs browser-based exploration of external links and recording results, but it does not explain data-handling boundaries for third-party sites. While much of this content may be public, opening and persisting off-platform findings can expose browsing metadata, collect more personal data than expected, and create unclear retention/privacy practices.

VirusTotal

65/65 vendors flagged this skill as clean.