Security audit
GPT Image 2.6 电商主图生成 | 商品主图套图 | 高点击率首图 | SKU 图制作
Security checks for vulnerabilities and agentic risk
Overview
This skill provides a clearly scoped product-image workflow with disclosed uploads and user confirmation before paid generation.
Use images you are authorized to send to Qinghu, verify the configured service destination, and confirm the quoted credits before generation. The external CLI is installed globally without a fixed version and was not code-audited here. The scanner's partial status reflects runtime-generated JSON references, which were independently checked against the instructions.
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