ClawHub
Back to skill

Security audit

豆包AI图像生成

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward browser-automation guide for generating images with Doubao, with disclosed local saving and optional delivery behavior.

Before installing, be comfortable with the agent using Doubao in a browser, saving images under the workspace, and sending generated images to Feishu or another destination when requested. Avoid sensitive prompts or images unless the destination and service terms are acceptable.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly includes delivering generated images to Feishu chat or other external destinations, but it does not warn users that generated content may be transmitted outside the local environment. This creates a real data-handling and privacy risk because prompts or images may contain sensitive business or personal information and could be shared to third-party systems without informed user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The workflow instructs the agent to click on specific Chinese UI labels ("图像生成" or "AI 创作") with no indication that this depends on a Chinese-language interface or that alternatives may exist. This imposes a locale-specific behavior without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.