ClawHub
Back to skill

Security audit

mdapi.io

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed mdapi.io integration for converting user-provided content, with no executable installer or hidden local behavior.

Use this skill only for content you are comfortable sending to mdapi.io. Avoid submitting secrets, credentials, regulated data, private source code, or internal URLs unless you have approval, and be careful enabling autonomous payment or storing paid tokens in tool configuration.

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
94% confidence
Finding
The skill directs an agent to send user-supplied URLs, files, text, and prompts to mdapi.io, but it does not require explicit user consent or a clear warning that content will leave the local environment. In agent settings, this can lead to unintended disclosure of sensitive documents, proprietary source material, secrets embedded in files, or confidential prompts to a third-party service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.