ClawHub

KrumpClaw

Security checks across malware telemetry and agentic risk

Overview

KrumpClaw appears purpose-built for Moltbook posting, but it gives an agent public posting/commenting authority without clear per-action approval safeguards.

Install only if you intend to let an agent interact with Moltbook using your account. Keep the API key in an environment variable or secret store instead of TOOLS.md, require the agent to draft and ask before every post or comment, and avoid using the included shell helper with untrusted title or content until its JSON construction is hardened.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent/user to configure an API key and provides authenticated POST examples for creating posts and comments, but it does not clearly warn that these actions will publish content under the user's account or require explicit consent per action. In an agent-skill context, this can lead to unintended account activity, reputation damage, and abuse if the skill is invoked automatically or misunderstood.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description presents the skill as an autonomous agent that can post, comment, and track league activity without defining activation boundaries, approval requirements, or user-trigger constraints. In a skill with network and file system capabilities, this broad scope can enable unintended or unauthorized actions, increasing the risk of spam, impersonation, or misuse if the agent is invoked too freely.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Post a Lab session
curl -X POST "https://moltbook.com/api/v1/posts" \
  -H "X-API-Key: $MOLTBOOK_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
88% confidence
Finding
curl -X POST "https://moltbook.com/api/v1/posts" \ -H "X-API-Key: $MOLTBOOK_KEY" \ -H "Content-Type: application/json" \ -d '{ "title": "🧪 KrumpClaw Lab - [Topic]", "content": "[Your lab

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal