ClawHub
Back to skill

Security audit

Agent Orchestrator

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed multi-agent orchestration skill, with file and workspace changes that fit its stated purpose but should be used deliberately.

Install only if you want an agent to coordinate other agents and create orchestration files. Before running it, confirm the target workspace, what files may be copied or generated, and whether cleanup/archive actions are acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
92% confidence
Finding
The mandatory trigger list contains broad operational phrases such as 'orchestrate', 'decompose task', and 'delegate tasks' that can plausibly appear in ordinary user requests, increasing the chance this skill activates when the user did not intend to invoke a meta-agent. In this skill's context, unintended activation is more dangerous than usual because activation leads to spawning sub-agents, generating new SKILL.md files, and creating/modifying multiple workspace files, amplifying the effect of a mistaken match.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the orchestrator to create agent workspaces, write instruction files, copy inputs, track status, and later clean up or archive temporary files, but it does not clearly warn the user up front that these filesystem operations will occur across multiple directories. In this context, the omission is significant because the skill automates broad file creation and cleanup as part of agent spawning and dissolution, which can surprise users and increase the risk of unintended data modification or deletion.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.