Back to skill

Security audit

AI绘画提示词优化器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-writing helper for AI art tools and does not request code execution, credentials, persistence, or broad local access.

Install this if you want a Chinese-oriented AI art prompt assistant that usually converts requests into English platform prompts. Review generated prompts before using them in external image tools, especially if you need a different language, stricter content boundaries, or exact platform versions.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The markdown states that English works better for DALL-E and that Flux 'must be English', which imposes a language constraint in the skill behavior. This is a natural-language locale policy concern because the file does not present this as a user choice or opt-in, despite the skill otherwise serving Chinese-speaking users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file content is entirely in Chinese and presents the skill as operating in that language by default, without indicating language negotiation or honoring the user's preferred locale. This can cause confusing or inaccessible behavior for users expecting another language, and in agent settings it may override user intent or reduce the user's ability to safely review generated prompts and parameters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.