Security audit
structs-guild-stack
Security checks for vulnerabilities and agentic risk
Overview
This skill clearly documents an advanced local Docker Compose stack for game-state indexing and warns about its persistent services and optional signing component.
Install only if you intentionally want a persistent local Docker-based game-state indexing stack. Pin a release tag, review the Compose file before starting services, use the recommended read-only service set first, keep the transaction signing daemon disabled unless you have reviewed its code and isolated a low-balance key, and tear the stack down when you no longer need it.
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.