ClawHub
Back to skill

Security audit

X-search-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward X/Twitter search helper that sends user-provided search terms to xAI as disclosed by its purpose and setup instructions.

Install this only if you are comfortable sending your X/Twitter search terms, filters, and xAI API key-authenticated requests to xAI. Keep the API key scoped and protected, and avoid searching sensitive personal or confidential terms through this skill.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill invokes Python, requires an API key from the environment, and makes outbound network requests, but it does not declare an explicit tool scope such as permissions or allowed-tools. That weakens least-privilege enforcement and makes the skill’s effective capabilities less transparent to the host, increasing the chance of unintended execution with broader access than necessary.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation guidance includes expansive phrases like 'find tweets,' 'look up what people are saying on X,' and 'find social media posts about a topic' without clear boundaries or exclusion conditions. This makes activation scope ambiguous and increases the chance the skill is invoked for general social-media or research requests beyond the intended X-specific search use case.

External Transmission

Medium
Category
Data Exfiltration
Content
def redirect_request(self, req, fp, code, msg, headers, newurl):
        raise HTTPError(newurl, code, f"Redirect to {newurl} blocked (auth safety)", headers, fp)

API_URL = "https://api.x.ai/v1/responses"
MODEL = "grok-4.20-reasoning"
TIMEOUT_S = 120
MAX_HANDLES = 10
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends the user’s raw search query and selected filters to the external xAI API, but the code itself provides no explicit user-facing disclosure or consent mechanism at the point of transmission. In an agent skill context, users may assume local handling unless clearly told otherwise, so sensitive terms, names, or investigative queries could be exposed to a third party.

Static analysis

No suspicious patterns detected.