ClawHub
Back to skill

Security audit

网页浏览助手免费版

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward web-browsing instruction skill with broad but purpose-aligned tool declarations and no evidence of hidden execution, persistence, or data theft.

Install only if you are comfortable with a skill that can direct the agent to browse external websites and run web-browsing commands. Do not provide secrets, private/internal URLs, credentials, or sensitive query strings unless you intend them to be sent to external sites or search providers.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest grants exec and write capabilities, but the skill does not clearly disclose to users that it may execute shell commands and modify local files as part of its operation. Even if intended for benign browsing workflows, these capabilities materially expand the attack surface by enabling command execution side effects, local persistence, overwriting files, or chaining with unsafe user-controlled inputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill clearly performs external web fetches and searches against user-provided URLs and queries, but the documentation does not prominently warn users that their inputs will be sent to remote sites and search providers. This can expose sensitive prompts, internal URLs, tokens in query strings, or private research targets to third parties and may surprise users about the privacy and network side effects of using the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The examples set language to zh and zh-CN as defaults for summarization and search configuration, and the skill is otherwise presented as generally applicable rather than region-specific. This can constitute a language/locale policy issue because the documentation normalizes a fixed locale without explicitly offering user choice or noting that it is merely an example.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.