ClawHub
Back to skill

Security audit

Swarm Coder Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed coding-workflow helper that creates local prompt files and directs agent-based code review, with no evidence of hidden data access or exfiltration.

Install only if you want an agent-assisted coding workflow that may read project plans, modify repository files, run tests/commands, and create .swarm/ prompt files. Review generated changes before committing or submitting code, especially because the skill delegates implementation and review work to subagents.

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)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The bash example performs workspace-modifying actions such as creating directories and writing prompt files, and the surrounding documentation does not clearly warn users that these steps change local state or may trigger downstream coding and submission actions. In an agent skill context, examples are often copied verbatim or operationalized by automation, so missing safety framing increases the risk of unintended file modification or repository changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.