Security audit
gpt-image
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed RunAPI GPT Image helper that uses the RunAPI CLI to generate or edit images, with no artifact-backed signs of deception, persistence, or unrelated access.
Before installing, confirm you trust RunAPI and understand that prompts, referenced media files, and generated outputs may be sent through that service and may incur account costs. Use an environment API key or explicit token import, and only use browser login if you choose to do so.
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
Static analysis
No suspicious patterns detected.