ClawHub
Back to skill

Security audit

oya-browser

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed browser-automation tool, but it can use persistent logged-in browser personas, stored credentials, CAPTCHA/MFA flows, and automatic portal sign-ins across broadly scoped web tasks.

Install only if you are comfortable letting Oya operate persistent cloud Chrome personas that may already be logged in to sites. Before using it on accounts, payments, admin portals, healthcare portals, or private data, set clear task limits and require confirmation before submissions, destructive changes, purchases, moderation, credential use, MFA completion, or scraping authenticated content. Stop browsers after use because running sessions can cost money and preserve account state.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises itself for very broad tasks such as browsing, logging in, form filling, scraping, and running several browsers at once, without strong gating criteria for when it should or should not be invoked. In an agent environment, this can cause over-selection of a high-impact browser automation capability for ordinary requests, increasing the chance of unintended navigation, credential exposure, or execution of risky web actions on untrusted sites.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.