ClawHub
Back to skill

Security audit

Web Automation

Security checks for vulnerabilities and agentic risk

Overview

This browser automation skill is coherent, but it broadly enables authenticated browsing, cookie handling, form submission, and arbitrary site interaction without clear user-consent safeguards.

Review this skill before installing if you expect it to touch logged-in websites or sensitive accounts. It should be used only with explicit user direction for logins, cookie/session reuse, form submission, and actions that could change account or business data.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly supports session cookies, custom user agents, and portal logins but does not warn about the risks of credential handling, authenticated sessions, or interactions with sensitive accounts. This omission is dangerous because users or agents may employ the skill for login automation or session reuse without safeguards, increasing the risk of unauthorized access, session leakage, or unsafe actions on behalf of a user.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger guidance is overly broad because phrases like "browse", "check a website", and "login to a portal" are common user requests that can invoke powerful browser automation without sufficient narrowing conditions. In a skill that can navigate arbitrary URLs, manage cookies, and automate forms, broad activation increases the chance of unintended use on sensitive sites, credential workflows, or user sessions.

Content

No source excerpt is available for this finding.