ClawHub
Back to skill

Security audit

X-search-skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent X/Twitter search helper that sends user search terms to xAI using a declared API key, with no evidence of hidden persistence, file mutation, or unrelated behavior.

Install only if you are comfortable sending X/Twitter search queries and filters to xAI under your XAI_API_KEY. Keep the API key private, avoid using confidential search terms, and rotate the key if it is exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill requires environment access for `XAI_API_KEY` and makes outbound network requests to the xAI API, but no explicit permissions are declared. This weakens user awareness and policy enforcement, because a user or platform may invoke the skill without realizing it can access secrets and transmit data externally.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The description contains broad trigger language such as 'look up what people are saying' and 'find social media posts about a topic,' which can match many ordinary requests. Over-broad routing increases the chance the skill is invoked unexpectedly, causing user prompts to be sent to an external service when the user did not specifically ask for X search.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
Although the skill notes mention use of the xAI Responses API, the usage section does not clearly warn that user queries are transmitted to an external third-party service. In practice, this can lead to unintended disclosure of sensitive prompts or search terms, especially because the skill is designed for broad natural-language use.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.