Back to skill

Security audit

Jimeng Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped Jimeng image-generation helper whose browser use and local image downloads are disclosed and aligned with its purpose.

Install this if you want an agent to operate Jimeng through an OpenClaw-managed browser. Use a dedicated browser profile where possible, watch for credit or payment prompts, and remember that generated images will be saved locally unless you direct cleanup afterward.

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
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

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly instructs the agent to download generated files to the local filesystem and report the absolute path, but it does not require notifying the user beforehand or obtaining consent for local persistence. This creates a privacy and safety issue because browser-acquired content is being written locally by default, which may surprise users, leak sensitive data into the host environment, or leave residual files on shared systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.