ClawHub
Back to skill

Security audit

browserwing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a browser-automation helper with expected but powerful access that can type credentials, inspect pages, run JavaScript, capture screenshots, and view network activity without enough safety guidance.

Install only if you trust the BrowserWing executor you will connect to. Avoid using it on banking, admin, medical, workplace, or other sensitive sites unless you explicitly intend to expose that page content and any typed credentials to the executor. Prefer a local executor, review the target tab before actions, and do not provide passwords or secrets through this skill unless necessary.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The top-level description advertises page extraction, screenshots, JavaScript execution, console inspection, and network capture without any privacy or data-handling warning. These capabilities can expose page contents, credentials, tokens, personal data, internal URLs, and browser activity to the executor or downstream logs, so failing to disclose the privacy implications makes misuse more likely.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

bash
EXECUTOR_URL="${BROWSERWING_EXECUTOR_URL:-http://127.0.0.1:8080}"
curl -X GET "${EXECUTOR_URL}/api/v1/executor/help"

Response: Returns complete list of all commands with parameters, examples, and usage guidelines.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly documents login automation and credential entry but provides no warning that users may expose passwords, session data, or account access to the browser executor service. Because the executor can navigate, type credentials, inspect pages, and potentially capture screenshots or page content, omitting a credential-handling warning materially increases the risk of accidental secret disclosure and unsafe use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.