ClawHub
Back to skill

Security audit

Jarvis MCP HTML Extractor

Security checks across malware telemetry and agentic risk

Overview

This is a small, coherent web-scraping MCP skill, with expected network-fetching behavior but no evidence of hidden persistence, credential access, or destructive actions.

Before installing, verify that the npm package is the one you intend to run and consider pinning or testing it in an isolated environment. Use the skill only for URLs you trust the agent to fetch, and avoid internal, localhost, authenticated, or policy-restricted sites unless you explicitly intend that access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly supports fetching pages, extracting text, and calling JSON APIs against user-supplied URLs, but the documentation does not warn about outbound web requests, scraping behavior, or the trust boundary around URLs. In an agent context, this omission can lead to unsafe use such as SSRF-style access to internal endpoints, unexpected data exfiltration via remote requests, or policy violations around automated scraping.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.