Security audit
Polyphemus: The One-Eyed Image Forge
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently guides an agent to use Eye.Art's external image-generation MCP service, with the main user consideration being that prompts, page references, and uploaded images may be sent to Eye.Art.
Install this if you are comfortable using Eye.Art as an external image provider. Do not send private images, sensitive page contents, or confidential design material through the service unless you intentionally choose to share them.
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.