ClawHub
Back to skill

Security audit

智能抠图助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple background-removal guide that clearly centers on cloud image APIs, but users should understand that images may be sent to external services.

Before using this skill with personal, confidential, biometric, or customer images, assume uploads may be processed by Baidu, Tencent, or the listed demo website and review those services' privacy and retention terms. The package itself does not show hidden execution or persistence.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly states that the tool uses Baidu/Tencent image APIs, which implies user images are transmitted to third-party services, but it does not warn users about that data flow or its privacy implications. For an image-processing skill, this omission can mislead users into sharing sensitive photos without informed consent, especially when images may contain faces, personal items, or confidential content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly promotes 'cloud AI APIs' for background removal but does not disclose that user images will be transmitted to a third-party service for processing. Because images may contain faces, IDs, products, or other sensitive content, users could unknowingly expose personal or confidential data to an external provider with different retention, logging, or jurisdictional practices.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The 'Live Demo' section invites users to try an external website without warning that using the demo requires uploading images to a third-party web service. This is risky because users may test with personal, biometric, or commercially sensitive images and may not realize the external site can store, inspect, or reuse submitted content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The README content is predominantly in Chinese and does not indicate that users may choose another language or that the locale restriction is intentional. This can be a natural-language policy concern when a skill effectively forces a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.