ClawHub

Grok X Analyzer

Security checks across malware telemetry and agentic risk

Overview

This X/Twitter analysis skill is not malicious, but it asks agents to fetch content and delegate deeper work with broad, hidden activation that users may not notice.

Review before installing. Use this only if you are comfortable with the agent fetching X/web content, possibly through an authenticated xurl setup, and prefer explicit user confirmation before it fetches data or spawns subagents. Do not rely on the included helper script for accurate results unless it is repaired and its mock fallback behavior is removed or clearly labeled.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises and documents shell-capable operations such as `xurl` CLI commands and spawning subagents, but no explicit permissions model is declared in the skill metadata. That mismatch can enable unintended command execution pathways or broaden the effective capability surface without clear user or platform controls, especially in an auto-triggering skill.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger description is extremely broad, covering nearly any mention of X/Twitter URLs, analysis, summaries, engagement checks, trends, replies, or project-like breakdowns, and even emphasizes 'seamless, hidden activation.' Overbroad hidden activation increases the risk that the skill runs in contexts the user did not intend, causing unnecessary data access, tool use, or side effects.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The Quick Start examples instruct activation on vague phrases like 'analyze thread,' 'X trends,' and 'post engagement' without defining scope limits or when not to activate. In practice, this ambiguity can cause the skill to intercept unrelated requests and initiate external fetching or analysis workflows unexpectedly.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal