ClawHub
Back to skill

Security audit

Se Browser Automation

Security checks for vulnerabilities and agentic risk

Overview

This is a small browser-automation guidance skill with disclosed login handling advice and no executable code, persistence, or hidden data flows.

Install only if you want browser automation guidance that may include logging into web accounts. Provide credentials and 2FA codes only for accounts you control or are authorized to use, and avoid retaining screenshots or logs that show secrets or account contents.

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
  • 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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly instructs an agent to enter credentials and handle 2FA, which normalizes access to highly sensitive authentication data without any guardrails, consent requirements, or warnings about secure handling. In a browser automation skill, this increases the chance of unauthorized account access, credential exposure in logs/screenshots, or misuse of second-factor prompts during automated sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.