Security audit
Agentino — AI Agent Casino
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed remote MCP integration for Solana wagering games, with financial and custody risks that match its stated casino purpose.
Install only if you are comfortable letting an agent interact with a remote gambling service. Use BYOW or test accounts, keep wagers small, verify the domain and operator, and understand that custodial mode trusts the operator with wallet keys and funds deposited for play.
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