ClawHub
Back to skill

Security audit

x-twitter-post-generator

Security checks across malware telemetry and agentic risk

Overview

This is a documented external content-generation skill with some unclear examples and privacy caveats, but no hidden execution, persistence, or destructive behavior was found.

Install only if you are comfortable sending prompts, uploaded reference images, and generated content to the documented external services. Treat share URLs and hosted image URLs as potentially accessible outside your local machine, and do not assume the skill can safely publish directly to X/Twitter without separate, explicit publishing instructions and permissions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The Quick Start claims users can export and publish generated posts to X/Twitter instantly, but the documented API only returns assets and a workspace/share URL. This mismatch can mislead users about what the skill actually does and may cause them to disclose content or credentials under the false assumption that publication is handled safely and directly by the platform.

Intent-Code Divergence

Low
Confidence
88% confidence
Finding
The example output contradicts the documented x-twitter channel by returning a generic channel and a localhost-based share URL. This inconsistency can cause users or downstream agents to trust invalid endpoints or misunderstand where generated content is hosted, increasing the risk of accidental disclosure or failed validation of external destinations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not clearly warn that prompts, uploaded images, and generated outputs are sent to third-party services and exposed through share/export URLs. In a content-generation skill that encourages image uploads and returns workspace links, this omission is dangerous because users may unknowingly transmit sensitive data to external processors or create publicly accessible artifacts.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.