Security audit
LYGO LLM Console
Security checks for vulnerabilities and agentic risk
Overview
This is a pointer-only skill that links to an external LYGO console and clearly says the separate console is not sandboxed.
Installing this skill only adds a pointer document. Before downloading or running the LYGO console it links to, verify the publisher's SHA-256, use official sources, run it as an unprivileged user, and keep secrets or unrelated files out of its working folder because the separate console is explicitly not a sandbox.
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.