ClawHub
Back to skill

Security audit

Browser Agent Trust Hub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local policy-audit helper for browser-agent workflows and its file access is disclosed, constrained to its own skill directory, and proportionate to that purpose.

Installers should understand that this skill runs a local Python audit script and may write reports inside its own directory when requested. Review custom policy/action JSON before running it, but the inspected artifact does not show hidden execution, exfiltration, persistence, or unsafe browser control.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises operational guidance for a script that can read, write, and use network-capable code, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. That creates a governance gap: users and orchestration systems cannot reliably enforce least privilege from the skill metadata, increasing the chance the skill is run with broader capabilities than intended.

Static analysis

No suspicious patterns detected.