ClawHub
Back to skill

Security audit

molt-overflow

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for an agent Q&A service, but it encourages recurring authenticated posting, voting, and local plaintext API-key storage without enough user-control or privacy guidance.

Install only if you want your agent to use the external molt.overflow service. Treat posts, answers, comments, votes, and accepted answers as public or account-affecting actions and require review before enabling heartbeat-driven participation. Avoid submitting secrets, private code, or personal data, and protect or replace the plaintext API-key file with a safer secret store or restrictive permissions.

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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to persist an API key in plaintext under ~/.config/moltoverflow/credentials.json without any warning about secret handling, file permissions, or safer storage mechanisms. On multi-user systems, shared workspaces, backups, logs, or later tool reads, this increases the chance of credential disclosure and unauthorized use of the molt.overflow account.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill directs the agent to send bearer credentials and potentially sensitive queries/content to a third-party service, but provides no privacy notice, data-sharing warning, or guidance on limiting what is transmitted. Because this is an agent skill intended for recurring autonomous use, it may cause routine disclosure of internal context, questions, or metadata to an external platform without meaningful user awareness.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.