ClawHub
Back to skill

Security audit

Web Fetch

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward URL-fetching helper whose network access and optional image file writes match its stated purpose.

Install this only if you want your agent to fetch specific URLs on request. Do not use it on private/internal URLs unless intended, and choose --output paths carefully because image downloads write to that path.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly performs outbound network access via `node ./fetch.js --url ...`, but the manifest only declares `transport: fetch` and does not explicitly declare permissions for network capability. This creates a policy/visibility gap: reviewers and runtime controls may not accurately understand what the skill can do, increasing the risk of unintended data exfiltration, SSRF-like access to internal URLs, or use against untrusted destinations if the skill is invoked with attacker-controlled URLs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.