ClawHub

Userorbit

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate Userorbit API helper, but it gives an agent broad live authority to publish, change, and delete business content without clear safety guardrails.

Install only if you want an agent to operate on live Userorbit data. Use the least-privileged API key available, keep the token out of chat and logs, and require explicit approval before any publish, delete, archive, restore, subscriber, project, or bulk update action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent to use shell commands and make outbound network requests, but it declares only environment-variable requirements and no explicit permissions model. This mismatch can cause the skill to be granted more capability than reviewers or policy systems expect, increasing the risk of unintended command execution or data exfiltration through HTTP calls.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documentation tells the agent to use bearer tokens from environment variables in direct curl requests but provides no guidance on preventing accidental disclosure in logs, error messages, transcripts, or debugging output. Because these credentials authorize access to a live third-party service, poor secret handling could expose the API key and enable unauthorized operations against the Userorbit account.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents numerous state-changing and destructive operations such as delete, archive, restore, publish, unpublish, and update across many resource types, yet it gives no warning about their effects on production data or any confirmation/preview workflow. In an agent setting, this raises the chance of accidental destructive actions, mass content changes, or publishing mistakes caused by ambiguous user prompts or automation errors.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal