Build a Software Development Team

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed setup guide for creating an OpenClaw development team, with high-impact actions delegated to named admin, Asana, Git, and email skills.

Install this only if you intend to let it coordinate setup of multiple OpenClaw agents and project files. Review the delegated skills before use, especially openclaw-administrator, Asana, Git, and Email; keep real tokens in your secret manager, provide only env var names, and use the recommended recovery snapshots before and after setup.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger guidance is extremely broad and could cause the skill to activate for vague project-management requests without clear user intent for a high-impact setup operation. Because this skill writes configs, creates files, and clones repos, over-triggering raises the risk of unintended system modifications and delegated tool actions.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill description does not prominently disclose that execution will create and modify agent workspaces, write multiple coordination/configuration files, and clone a repository locally. Poor disclosure can undermine informed consent and lead users to trigger a materially state-changing skill without realizing its system impact.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal