Security audit
GPT Image 2.6 千川投流图生成 | 直通车广告图 | 信息流素材 | 钻展图
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a coherent image-generation workflow with disclosed uploads, protected API-key handling, and user confirmation before paid generation.
Install if you trust the external CLI and are comfortable sending the selected images and prompts to Qinghu. Check the account and service endpoint, keep the API key out of shared files, and review each generation's cost before confirming. The scanner's partial status was investigated: its missing JSON files are runtime outputs. The external CLI implementation remains outside this review.
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