ClawHub
Back to skill

Security audit

ScopeGate Client

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only safety gate that calls ScopeGate before consequential actions, but users should understand it sends action details and an API key to that service.

Install this only if you want ScopeGate to act as a fail-closed authorization check for consequential agent actions. Use a trusted ScopeGate URL, protect and rotate the API key if exposed, and avoid putting unnecessary sensitive details into requested_action text.

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
93% confidence
Finding
The skill instructs the agent to send an API key in a POST body to an external service and does not include any user-facing disclosure, trust boundary warning, or guidance on secret handling. Even if this is the intended design, transmitting credentials to a third-party endpoint from a generic skill increases credential exposure risk, especially because the endpoint is overrideable via the SCOPEGATE_URL environment variable.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
SCOPEGATE_URL="${SCOPEGATE_URL:-https://api.scopegate.ai}"

curl -s -X POST "$SCOPEGATE_URL/grant/verify" \
  -H "Content-Type: application/json" \
  -d '{
    "grant_id": "<grant_id from delegator>",
Confidence
95% confidence
Finding
curl -s -X POST "$SCOPEGATE_URL/grant/verify" \ -H "Content-Type: application/json" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.