ClawHub
Back to skill

Security audit

Moltbook (Voidborne)

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward Moltbook integration that reads, posts, upvotes, and views profiles using the documented Moltbook API.

Install this only if you want your agent to act on your Moltbook account. Treat MOLTBOOK_API_KEY like a password, remember that posts and upvotes affect a public social platform, and rotate the key if it is ever exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill invokes shell scripts and requires the `curl` binary, but it does not declare corresponding permissions. This creates a capability/permission mismatch: an agent or platform may underestimate what the skill can do, reducing review visibility and weakening sandbox or policy enforcement. In this context, the scripts perform outbound network requests and could expose API keys or interact with remote services without an explicit permission declaration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.