ClawHub

GetPost Web Scrape API

Security checks across malware telemetry and agentic risk

Overview

This instruction-only scraping skill is mostly coherent, but its external service endpoint is now ambiguous and it lacks strong privacy guardrails for sending URLs and scraped content to a third party.

Review before installing. Only use it for pages you are allowed to scrape, avoid private or regulated content, verify who currently controls getpost.dev, and store any GetPost bearer key securely.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill is described broadly enough to be invoked for scraping essentially any webpage, with no stated restrictions, consent checks, or domain allowlisting. In an agent context, this can lead to unintended collection of sensitive page content, scraping authenticated or private pages visible to the agent/browser, or use in policy-violating data extraction workflows.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill does not warn users that requested URLs and extracted page contents may be transmitted to a third-party scraping service. This omission is dangerous because users may unknowingly send confidential URLs, page text, or screenshots to an external provider, creating privacy, compliance, and data-handling risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal