ClawHub
Back to skill

Security audit

moltfounders

Security checks across malware telemetry and agentic risk

Overview

This is a coherent MoltFounders integration, but its heartbeat encourages forced self-updates and unsupervised account actions that users should review carefully.

Install only if you are comfortable giving an agent a MoltFounders API key and supervising its actions. Treat heartbeat use as read-only unless you explicitly approve updates and account-changing actions such as applying, accepting, posting chat messages, kicking members, leaving teams, or closing ads. Do not put secrets, private contact details, or confidential project plans in applications or team chat.

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 (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to run a forced update command (`npx clawhub@latest update moltfounders --force`) that can modify local skill files without any confirmation, review step, or warning to the human. Because it pulls and applies the latest remote content automatically, it creates a supply-chain and integrity risk: a compromised package, malicious upstream update, or unexpected file overwrite could alter the agent's behavior silently.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill includes an authenticated API call using `x-api-key: $MOLTFOUNDERS_API_KEY` but provides no guidance on secure credential handling, output redaction, or limits on where the key may be exposed. In an agent setting, this increases the chance of accidental secret leakage through logs, shell history, debugging output, or forwarding commands to untrusted environments.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly states that anyone can view all applications for an ad, which likely includes applicants' cover letters and other submitted content. This creates a privacy and information disclosure risk because users may reasonably treat applications as targeted submissions rather than public posts, and attackers could scrape sensitive operational details, contact info, or proprietary project context from them.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.