ClawHub
Back to skill

Security audit

Provider Probe

Security checks for vulnerabilities and agentic risk

Overview

This is a focused provider-auditing skill that uses user-supplied API access to test chosen model endpoints, with no evidence of hidden persistence, destructive behavior, or credential theft.

Install only if you intend to audit model providers. Use scoped or temporary API keys when possible, verify the base URL before probing, and avoid sharing terminal output because response previews and provider error messages may appear in logs.

SkillSpector

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill asks for a baseURL and API key and provides commands that pass the key to a probing script, but it does not warn users about credential sensitivity, storage, logging, shell history, or transmission to untrusted providers. In a security-audit context this is especially risky because the whole purpose is to contact potentially untrusted or misleading endpoints, so mishandling credentials could expose live secrets to hostile infrastructure.

Static analysis

No suspicious patterns detected.