ClawHub
Back to skill

Security audit

X Search Bwm

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward X/Twitter search helper that uses an xAI API key and sends user search queries to xAI as expected.

Install only if you are comfortable providing an xAI API key and sending X search queries, filters, and related prompt text to xAI. Avoid using it for secrets, regulated data, or proprietary topics unless that third-party sharing is acceptable.

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 network access to the xAI API, but those capabilities are not explicitly declared as permissions. This can reduce transparency and informed consent for users, who may invoke a skill without realizing it can exfiltrate prompts and use local secrets to access an external service.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The description uses broad trigger language such as 'find tweets', 'search X/Twitter', and 'look up what people are saying on X', which can cause the agent to invoke this skill in a wide range of ordinary conversations. Over-broad triggering increases the chance that user queries are unnecessarily sent to an external API and that actions occur without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The markdown explains setup and usage but does not clearly warn that search queries and returned social-media content are transmitted to the external xAI API/X search service. In this context, the omission is important because users may provide sensitive topics or identifiers, not realizing their inputs will leave the local environment and be processed by a third party.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.