ClawHub

Request Approval

Security checks across malware telemetry and agentic risk

Overview

This is a safety-oriented approval skill with no hidden code, but users should configure its Preloop token and approval rules carefully.

Before installing, verify the Preloop MCP endpoint or npm package you configure, use a dedicated least-privilege Preloop token stored securely, and set your approval policy so destructive or sensitive actions still require approval even in dev or staging environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
91% confidence
Finding
The setup documentation instructs users to place a bearer token directly into a JSON configuration example but does not warn that the token is a secret, should not be hardcoded, and should be stored using secure secret-management mechanisms. This can lead to accidental credential exposure through source control, screenshots, shared config files, or local compromise, especially because the file is operational setup guidance.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
2. **Conditional logic**:
   - If production: Call `request_approval` (as shown above)
   - If dev/staging: Proceed directly without approval

3. **Tell the user**:
   - Production: "I've requested approval for this operation. Waiting for response..."
Confidence
91% confidence
Finding
without approval

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
3. **Tell the user**:
   - Production: "I've requested approval for this operation. Waiting for response..."
   - Dev/Staging: "This is a development environment, so I'm proceeding directly without approval."

## Example 7: Bulk File Operations
Confidence
93% confidence
Finding
without approval

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal