ClawHub
Back to skill

Security audit

Duoplus Ai

Security checks across malware telemetry and agentic risk

Overview

This skill clearly discloses that it controls DuoPlus cloud phones with a user-provided API key, and the sensitive behavior fits that purpose.

Install this only if you want an agent to control DuoPlus cloud phones. Provide the API key only for tasks you intend to run, review requests that power on/off/restart phones or change proxy settings, and remember that screenshots may be saved on disk.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to use environment variables, write screenshot files, and make authenticated network requests, but it does not declare corresponding permissions or boundaries. That mismatch can cause users or the platform to underestimate the skill's ability to exfiltrate sensitive data, persist artifacts locally, or perform remote actions against cloud devices.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The default prompt is broadly phrased to 'manage and automate a cloud phone' and to ask directly for an API key if one is not provided, without limiting when the skill should be invoked or what user confirmation is required. In a capability-rich skill that can inspect device state, control apps, and perform UI actions on remote Android phones, this broad activation scope increases the chance of inappropriate invocation, over-collection of secrets, and unintended execution of sensitive actions.

Missing User Warnings

Medium
Confidence
77% confidence
Finding
The code decodes screenshots returned from the gateway and writes them to an arbitrary user-supplied path on local disk. In this skill's context, screenshots can contain highly sensitive UI content from cloud phones, including credentials, OTPs, account data, or messages, so silent persistence materially increases confidentiality risk and forensic residue on the host.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/control-api.md:24