ClawHub
Back to skill

Security audit

Pluribus

Security checks across malware telemetry and agentic risk

Overview

This appears to be a peer-coordination skill whose network sharing and local identity lookup fit its purpose, but users should treat synced data as shared externally.

Before installing, assume announce/discover/sync may share node metadata and signal contents with Moltbook or peers. Do not place secrets, private prompts, customer data, or sensitive operational details in offers, needs, or signals, and review the init script's access to your Moltbook credentials file if that file contains tokens.

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 (2)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The README explicitly describes peer discovery and synchronization over Moltbook DMs and local sharing of agent data, but it does not warn users that offers, needs, signals, peer identities, and other workspace data may be transmitted to third parties. In an agent skill context, this omission is security-relevant because operators may unintentionally expose sensitive operational data or prompts to untrusted peers or an external service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs users to run announce/discover/sync operations that send node details and signals through Moltbook DMs and later potentially HTTP endpoints, but it does not warn that local data will leave the workspace and be shared over external channels. In an agent-to-agent coordination skill, this omission increases the risk of unintentional disclosure of identity, capabilities, observations, or sensitive operational data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.