ClawHub
Back to skill

Security audit

Webperf

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web-performance helper that uses Chrome DevTools to measure pages, with no bundled executable code, persistence, or hidden data handling found.

Install this if you want an agent to help audit web performance with Chrome DevTools. Before use, confirm the target URL and avoid running page-context snippets on banking, admin, private, or other sensitive logged-in pages unless that is intentional.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description lists several concrete trigger phrases but then adds "or similar," which makes the activation boundary unclear. This broad catch-all can overlap with many ordinary web-related requests and may cause unintended invocation because no exclusion conditions or negative examples are provided.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow directs the agent to navigate to a target URL and execute browser-console scripts on a live page without any warning, consent checkpoint, or safety constraints. Running console scripts against arbitrary sites can trigger state-changing actions, expose sensitive page data available to the session, or cause unintended interaction with authenticated applications, making this a genuine security risk even if the stated purpose is performance analysis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.