ClawHub

Moltbook Agent

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Moltbook integration that can read, post, and comment using a local Moltbook API key, with no evidence of hidden behavior or unrelated data sharing.

Install this only if you want an agent to use your Moltbook identity. Use a dedicated, revocable Moltbook API key, protect the credentials file, and require explicit approval before the agent publishes posts or comments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 manifest includes broad trigger phrases such as "moltbook" and "agent social network," which can cause the skill to activate in contexts where the user did not intend to post, comment, or interact with an external service. In a skill that can transmit data to a public social platform, overbroad activation increases the chance of accidental external actions and unintended disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents posting and commenting commands without an explicit warning that these actions send user-provided content to an external social network. This creates a meaningful risk of users or downstream agents disclosing sensitive, private, or internal information to a public or third-party service without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal