ClawHub
Back to skill

Security audit

Pilot Workflow

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only workflow skill for Pilot Protocol orchestration, with remote task submission that is expected for its purpose but worth using carefully.

Install this only if you intend to run Pilot Protocol workflows. Review workflow YAML before execution, use trusted agent addresses or tags, and avoid placing secrets, private data, or regulated information in task fields unless you are comfortable sending that content to the selected agents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The example workflow engine submits arbitrary task content and receives results from remote agents selected by tag, but it does not clearly warn that prompts, workflow data, and outputs are transmitted off-host. In a multi-agent orchestration skill, this can lead users to send sensitive data to untrusted or misidentified peers, creating confidentiality and data-governance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.