ClawHub
Back to skill

Security audit

Api Gateway Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only API gateway helper, with command execution used for documented CLI examples rather than hidden or destructive behavior.

Install only if you are comfortable routing read-only third-party service queries through the hosted api.maton.ai gateway. Use least-privilege/read-only scopes, confirm whether your setup expects API_KEY or MATON_API_KEY, do not paste secrets into chat, and review returned third-party data before relying on it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill declares the `exec` capability even though its documented purpose is a hosted, read-only API gateway. Granting shell execution unnecessarily expands the attack surface: a compromised or prompt-injected workflow could execute local commands, access environment variables such as API keys, or perform unintended network activity beyond the stated read-only scope.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.