x-research-kit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent X/Twitter research helper, but it tells users to use browser cookies without clearly warning that this can expose a logged-in account session.

Use unauthenticated extraction first. Only use the browser-cookie option if you intentionally want the tool to act with your logged-in X/Twitter session, and avoid using it for private, protected, or unauthorized content. Treat any cookie-derived data as sensitive and do not share logs, transcripts, or outputs that contain session material.

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
83% confidence
Finding
The skill is designed to extract content from X/Twitter, which can include personal data, account activity, and content from authenticated sessions, but it does not provide privacy or data-handling warnings near the outset. In a research/extraction context, omission of these warnings can lead users to collect or expose sensitive information without understanding the risks.

Missing User Warnings

High
Confidence
98% confidence
Finding
The documentation instructs users to export browser cookies for authenticated access without warning that cookies may contain active session credentials. This creates a real risk of credential exposure, account takeover, or unintended disclosure if the command output, shell history, logs, or shared environments are compromised.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal