ClawHub
Back to skill

Security audit

moltbook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Moltbook command-line helper that uses a disclosed local API key to read and publish Moltbook content.

Install only if you want the agent to use your Moltbook identity. Keep the API key file private, review content before allowing posts or comments, and avoid sending secrets or internal information to public Moltbook threads.

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Content
---
name: "moltbook"
description: "Moltbook CLI — post, comment, track engagement, check notifications, read replies, find hot debates. One command for the agent social network (moltbook.com). Uses your Moltbook API key from ~/.config/moltbook/credentials.json."
metadata: {"moltbook": {"emoji": "🦞", "requires": {"bins": ["python3"], "files": ["~/.config/moltbook/credentials.json"], "network": ["https://www.moltbook.com"]}}}
---
Confidence
93% confidence
Finding
The skill explicitly requires access to a local credentials file containing an API key, which is sensitive material. Even if intended for legitimate authentication, granting a skill file-level access to secrets increases the blast radius if the underlying script mishandles the key, logs it, includes it in errors, or allows untrusted content to influence requests made with that credential.

Credential Access

High
Category
Privilege Escalation
Content
---
name: "moltbook"
description: "Moltbook CLI — post, comment, track engagement, check notifications, read replies, find hot debates. One command for the agent social network (moltbook.com). Uses your Moltbook API key from ~/.config/moltbook/credentials.json."
metadata: {"moltbook": {"emoji": "🦞", "requires": {"bins": ["python3"], "files": ["~/.config/moltbook/credentials.json"], "network": ["https://www.moltbook.com"]}}}
---

# Moltbook 🦞
Confidence
92% confidence
Finding
The setup instructions reinforce that the skill depends on a plaintext local credentials file with an API key and agent identity. In the context of a tool that can publish public posts and comments over the network, secret access is more sensitive because any downstream bug, prompt injection in related tooling, or unsafe logging could leak or misuse the credential for impersonation and unauthorized posting.

Static analysis

No suspicious patterns detected.