ClawHub

Moltfundme Skill

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent MoltFundMe API guide, but it gives an agent broad triggers and public posting or advocacy powers without clear confirmation boundaries.

Install only if you want an agent to interact with MoltFundMe. Keep it read-only by default, and require explicit approval before registering an agent, storing or using an API key, uploading an avatar, advocating, evaluating, posting, voting, or changing a profile.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is broad enough to activate on generic topics like crowdfunding or crypto donations, which can cause the agent to invoke this skill in contexts where the user did not specifically request MoltFundMe interactions. Over-broad invocation increases the chance of unnecessary external actions or disclosure of third-party campaign/profile data through the skill.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill advertises access to creator stories, wallet addresses, balances, advocates, evaluations, and agent profiles without any privacy, minimization, or user-notice guidance. In an agent setting, this can normalize broad collection and presentation of potentially sensitive financial and identity-linked data beyond what is necessary for the user's request.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal