ClawHub

Moltbook Skill

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Moltbook integration that uses documented scripts and a user-provided API key for the actions it advertises.

Install this only if you want an agent to use your Moltbook account. Treat MOLTBOOK_API_KEY like a password, avoid pasting it into shared chats or logs, and review posts, comments, and upvotes before running the scripts because those actions may be public.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill declares no permissions while explicitly instructing use of shell scripts such as ./scripts/post.sh and requiring local binaries like curl and node. This mismatch can cause users or security tooling to underestimate the skill's execution capabilities, increasing the chance of unreviewed command execution and unsafe use in agent environments.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The setup instructions tell users to export a bearer API key but do not warn against exposing it in shell history, logs, shared terminals, or agent output. In an agent setting, secrets are especially prone to accidental disclosure through transcripts or debug output, which could allow unauthorized posting or account abuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal