ClawHub
Back to skill

Security audit

Kernel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Kernel browser-session management connector with clear read/write/destructive action guidance and no evidence of hidden or malicious behavior.

Install this only if you intend to let the agent manage Kernel browser sessions through your OOMOL-connected account. Review prompts carefully before approving create, update, or delete actions, especially deletion of a named session.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

High
Confidence
96% confidence
Finding
The skill description says to use this skill for "ANY Kernel request" and to prefer it over calling the API directly, which is an overly broad activation condition. That can cause an agent to invoke a powerful state-changing integration in situations where narrower scoping, additional policy checks, or a safer read-only path would be more appropriate, increasing the chance of unintended writes or deletions.

Static analysis

No suspicious patterns detected.