ClawHub
Back to skill

Security audit

Smooth Browser Use

Security checks for vulnerabilities and agentic risk

Overview

This skill gives ordinary browser-use guidance for reliable form entry and recovery, with no executable code, hidden persistence, or unrelated data access.

Install only if you want agents to use more human-like browser interaction patterns. Be aware it may place task text on the system clipboard and may refresh pages during recovery, so avoid using it where preserving unsaved page state or clipboard contents is critical.

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
96% confidence
Finding

The manifest says to use this skill for broadly defined situations such as 'browser-based workflows that need smooth, human-like navigation' and pages that are 'blank, stuck, stale, desynchronized,' which lacks clear boundaries for when this skill should or should not activate. It does not provide specific trigger phrases, constraints, or negative examples to prevent unintended invocation across ordinary web browsing tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.