ClawHub

TaskSquad.ai

Security checks across malware telemetry and agentic risk

Overview

TaskSquad’s purpose is clear, but it asks users to install a local daemon that can run remotely assigned work and stream logs without enough safety boundaries.

Install only if you trust TaskSquad, its installer source, and everyone who can assign tasks to your agents. Prefer a verified package or inspect and verify the installer before running it, use a low-privilege account and narrow working directory, treat tokens as secrets, assume logs and live streams may reveal local data, and confirm how to stop, revoke, or remove the daemon before connecting real projects.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly states that a daemon will pull tasks from a central portal and that agents execute those tasks locally, but it provides no warning about the security implications of running remotely assigned work on the user's machine. In this context, that omission is dangerous because the core function of the skill is remote task dispatch plus local execution, which can expose local files, credentials, and system resources if tasks are malicious or compromised.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The installation instructions recommend piping a remote script directly into bash without any verification, checksum validation, or trust warning. This is dangerous because a compromised install host, MITM in a misconfigured environment, or malicious script update would immediately yield arbitrary code execution on the user's machine.

External Transmission

Medium
Category
Data Exfiltration
Content
Connect via Server-Sent Events to watch agent activity in real-time.

```bash
curl "https://api.tasksquad.ai/live/:agentId" \
  -H "Authorization: Bearer $TOKEN"
```
Confidence
90% confidence
Finding
https://api.tasksquad.ai/

External Transmission

Medium
Category
Data Exfiltration
Content
Retrieve execution logs for a task.

```bash
curl "https://api.tasksquad.ai/tasks/:taskId/logs" \
  -H "Authorization: Bearer $TOKEN"
```
Confidence
90% confidence
Finding
https://api.tasksquad.ai/

External Script Fetching

High
Category
Supply Chain
Content
Using installation script (macOS/Linux/Windows):

```
curl -sSL install.tasksquad.ai | bash
```

### Prerequisite: tmux
Confidence
99% confidence
Finding
curl -sSL install.tasksquad.ai | bash

Chaining Abuse

High
Category
Tool Misuse
Content
Using installation script (macOS/Linux/Windows):

```
curl -sSL install.tasksquad.ai | bash
```

### Prerequisite: tmux
Confidence
98% confidence
Finding
| bash

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal