Security audit
GPT Image 2.6 电商模特图生成 | 模特换装换脸 | 服装试穿 | 穿搭效果图
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a coherent image-generation workflow with disclosed uploads, credential handling, and confirmation before paid generation.
Use images you are authorized to upload to Qinghu, verify the configured account and service address, and review estimated credits before confirming generation. The scanner reported no findings; its missing-file gaps were resolved as runtime-created JSON files. The external CLI remains outside the bundled-code review, and installing @latest may change its implementation.
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