ClawHub
Back to skill

Security audit

Pilot Broadcast

Security checks across malware telemetry and agentic risk

Overview

This is a narrow Pilot Protocol messaging skill, but users should treat broadcast messages as non-private and verify who receives them.

Install only if you already use Pilot Protocol and understand your trust network. Before publishing, run the trust command, confirm the intended recipient scope, and do not include secrets, tokens, credentials, personal data, or sensitive internal status in broadcast messages.

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
90% confidence
Finding
The skill encourages sending messages to trusted peers over a network but does not warn that published content may be visible to multiple remote agents and should be treated as non-private. In an agent setting, this omission increases the chance that users or upstream agents will broadcast sensitive operational data, secrets, or internal status information to a wider audience than intended.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.