Web Crawling Html API

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 8:03 PM UTC
• Version:
  1.0.0

Overview

This skill is a narrow Just Serp API wrapper for fetching webpage HTML, with privacy cautions around URLs and returned page content.

Install only if you are comfortable sending target URLs to Just Serp API and receiving raw page HTML back. Use it for public or authorized pages, avoid sensitive or internal links, and avoid logging or sharing returned HTML without checking for private data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly accepts a user-supplied URL and sends it to an external crawling service to retrieve full raw HTML, but the manifest provides no warning about outbound network access or third-party data transmission. This can lead to unintended disclosure of sensitive URLs, tokens embedded in query strings, intranet addresses, or user-provided private resources, especially if an agent invokes the tool without making the network action clear to the user.

Missing User Warnings

Low

• Confidence: 91% confidence
• Finding: The documentation describes an endpoint that fetches and returns full raw HTML from arbitrary user-supplied URLs, but it does not warn users that responses may contain sensitive page content, tokens embedded in markup, internal application data, or legally restricted scraped material. In an agent skill context, this omission can lead downstream agents or users to fetch untrusted or internal URLs and then process or expose the returned HTML without appropriate safeguards.

VirusTotal

63/63 vendors flagged this skill as clean.