ClawHub
Back to skill

Security audit

Web Page Markdown Content API

Security checks across malware telemetry and agentic risk

Overview

The skill performs one clear web-to-Markdown API task, but it exposes the service token through command arguments and a query parameter without enough warning.

Install only if you are comfortable sending target URLs to JustOneAPI. Avoid private, intranet, localhost, presigned, or secret-containing URLs, and treat the API token carefully because this version passes it through command-line arguments and a URL query parameter.

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

Medium
Confidence
98% confidence
Finding
The skill requires the API authentication token to be sent as a URL query parameter, and the code injects it directly into the request URL. Query-string secrets are commonly exposed in logs, browser/history equivalents, monitoring tools, reverse proxies, and upstream services, making accidental credential disclosure significantly more likely even when HTTPS is used.

VirusTotal

64/64 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