ClawHub
Back to skill

Security audit

Doubao Image Gen 豆包图片生成

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Doubao image-generation workflow, with a disclosed but persistent local save location users should understand.

Before installing, be aware that selected generated images are meant to be saved and copied to a persistent D drive folder. Avoid using sensitive or proprietary prompts/images unless that storage behavior is acceptable, and delete saved outputs manually when no longer needed.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to download generated images and copy them to a persistent local path on the D drive, but it does not require informing the user, obtaining consent, or defining retention limits. This creates a privacy and data-handling risk because generated images may contain sensitive, proprietary, or personal content that is silently stored outside the immediate task flow.

Static analysis

No suspicious patterns detected.