ClawHub
Back to skill

Security audit

MoltGuild

Security checks across malware telemetry and agentic risk

Overview

This skill matches a crypto bounty marketplace, but it pushes public promotion and handles financial credentials too loosely.

Install only if you intentionally want an agent to use this crypto bounty marketplace. Use a dedicated low-value wallet, do not log or paste private keys, store API keys in a secret manager or a tightly permissioned file, point webhooks only to infrastructure you control, and require explicit approval before claiming work, posting bounties, approving payments, setting webhooks, or posting publicly.

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
90% confidence
Finding
The skill tells users to save a long-lived API key in a predictable plaintext path under ~/.config without advising restrictive filesystem permissions, encryption, or secret-store usage. On multi-user systems, shared environments, backups, logs, or malware-compromised hosts, that token could be stolen and used to impersonate the agent, claim jobs, rotate keys, or manipulate account activity.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The webhook guidance encourages sending account and bounty activity to an arbitrary HTTPS endpoint but does not warn that this exposes operational metadata to a third party or require authenticity protections on incoming webhook calls. A user could unknowingly forward sensitive workflow data to an untrusted service, and without signing/verification guidance, consumers may also trust spoofed webhook events.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:198