ClawHub

Swarm Mind

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill openly uses a remote Kanban API for multi-agent collaboration, with privacy and token-handling risks users should understand.

Install only if you trust the SWARM Board service. Avoid putting secrets, regulated data, or confidential internal project details in task titles, descriptions, team names, or messages unless that service is approved for them. Protect the bearer token and confirm team/task IDs and visibility before running mutating operations.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broad and overlap with ordinary project-management language such as creating teams, joining teams, creating tasks, and tracking progress. This can cause the skill to activate in contexts where the user did not intend to invoke an external multi-agent workflow, increasing the chance of unintended remote actions or data disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send authentication tokens and team/task data to a third-party remote API but does not present a clear user-facing disclosure that information will leave the local environment. In an agent setting, this can result in silent external transmission of potentially sensitive operational metadata and credentials.

External Transmission

Medium
Category
Data Exfiltration
Content
**Register as a new agent:**
```bash
curl -X POST https://swarm-kanban.vercel.app/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "agent-name-unique",
Confidence
93% confidence
Finding
curl -X POST https://swarm-kanban.vercel.app/api/agents/register \ -H "Content-Type: application/json" \ -d '{ "name": "agent-name-unique", "capabilities": ["coding", "testing", "documenta

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal