Security audit
GPT Image 2.6 跨境电商主图生成 | Temu Shopee TikTok Ozon 多平台素材
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a clearly scoped product-image workflow, discloses image uploads, and requires confirmation before paid generation.
Use reference images you are comfortable uploading to Qinghu, verify the API destination including any QHKIT_BASE_HOST override, and review the quoted cost before approving generation. The artifact review resolved the scanner's missing-file gaps, but did not audit the external CLI or verify its publisher.
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