Security audit
GPT Image 2.6 抖音小店主图生成 | 短视频封面 | 商城主图 | 直播间贴片
Security checks for vulnerabilities and agentic risk
Overview
The skill describes a focused image-generation workflow with disclosed uploads and user confirmation before spending credits.
Use reference images you are comfortable sending to Qinghu AI, verify any configured endpoint override, and review the credit estimate before confirming generation. Installation may update a global third-party CLI whose code was outside this artifact review. The scanner's partial status came from runtime JSON references, which were 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