Lobster Config Guide
Security checks across malware telemetry and agentic risk
Overview
This is a text-only configuration guide whose advice matches its stated purpose and does not request hidden access, credentials, code execution, or data transfer.
Before applying the guide, review any AGENTS.md, customPrompt, temperature, or plugin-whitelist changes because they can alter how your agent behaves after restart. Only enable permissions for skills you trust. SkillSpector and static scan reported no issues, and the pending VirusTotal status is not a negative artifact signal.
SkillSpector
By NVIDIA
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
VirusTotal
64/64 vendors flagged this skill as clean.