ClawHub
Back to skill

Security audit

Web Page HTML Content API

Security checks across malware telemetry and agentic risk

Overview

This is a narrow JustOneAPI webpage HTML fetcher, but it handles the API token in ways that can expose it outside the immediate command.

Install only if you are comfortable sending requested URLs to JustOneAPI and using a JustOneAPI token with this helper. Avoid sensitive internal, authenticated, or pre-signed URLs, and prefer a revised version that reads the token directly from the environment or uses header-based authentication instead of command-line and query-string token handling.

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)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill transmits the API token as a query parameter, which is commonly logged by clients, proxies, load balancers, browser history, and server access logs. Even though the request uses HTTPS, placing secrets in the URL increases accidental exposure risk well beyond normal header-based authentication.

Vague Triggers

Low
Confidence
89% confidence
Finding
The skill exposes a generic URL-fetching capability with no documented constraints on allowed destinations, schemes, or use cases. In an agent environment, this can enable arbitrary remote fetching, which may be abused for server-side request forgery–style access to internal resources, metadata endpoints, or other unintended network targets if the backend honors attacker-controlled URLs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:41