ClawHub

Safe Action

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only safety preflight skill that clearly discloses its external checks and does not request credentials or local system control.

Install only if you are comfortable sending brief descriptions of planned high-risk actions, platform names, and timezone information to AgentUtil services. Avoid including secrets, customer data, private document contents, or detailed internal identifiers in action descriptions, and be aware that paid checks may incur small x402 charges.

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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
**HTTP fallback:**
```bash
curl -X POST https://think.agentutil.net/v1/check \
  -H "Content-Type: application/json" \
  -d '{"action": "database_migration", "description": "Drop column users.email in production"}'
```
Confidence
92% confidence
Finding
curl -X POST https://think.agentutil.net/v1/check \ -H "Content-Type: application/json" \ -d '{"action": "database_migration", "description": "Drop column users.email in production"}' ``` Note th

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal