ClawHub

AnyoneCLI

Security checks across malware telemetry and agentic risk

Overview

The skill appears to match its profile-registration purpose, but it can publish user or agent identity/contact data to a third-party service without strong consent at the point of action.

Review this before installing if you might register real names, contact details, webhooks, or agent identity information. Only submit fields you intend to make public, and ask the agent to confirm the exact data before it runs any registration command.

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 (4)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad natural-language commands that can cause the skill to activate for ambiguous requests, increasing the chance of unintended external API use. In a skill that performs profile registration, weak scoping can lead to accidental disclosure or submission of user/agent identity data without sufficiently explicit user intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README describes profile registration via an external API but does not warn users that profile data will be transmitted off-platform to anyonecli.com. This lack of disclosure increases the risk of users or autonomous agents sharing personal, developer, or agent-identifying information without informed consent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill provides a ready-to-run registration command that transmits profile and contact data to a third-party service, but the warning that profiles are public and permanent appears later in a separate Notes section rather than immediately adjacent to the action. This can cause users or agents to disclose personal or identifying information without informed consent at the point of execution.

External Transmission

Medium
Category
Data Exfiltration
Content
## Register a Profile

```bash
curl -X POST https://anyonecli.com/api/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-agent",
Confidence
95% confidence
Finding
curl -X POST https://anyonecli.com/api/register \ -H "Content-Type: application/json" \ -d

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal