ClawHub
Back to skill

Security audit

The Swarm

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local orchestration helper that writes coordination and audit files locally, with no artifact evidence of hidden network use, credential theft, or destructive behavior.

Install this only if you want an agent workflow helper that stores coordination state and audit history in local files. Avoid putting secrets, API keys, customer data, or personal information into permission justifications or project-context entries, and do not treat its grant tokens as real authorization for payments, databases, or exports without a separate human or platform approval gate.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill directs the agent to use it for ANY The Swarm-related request instead of calling the API directly, which is an overly broad trigger that can force unnecessary tool use. Broad routing language can cause the agent to invoke external data access in situations where a narrower, context-aware choice would be safer or more appropriate, increasing the chance of unintended data exposure or misuse of connected credentials.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.