Security audit
Lobster Cli Anything
Security checks across malware telemetry and agentic risk
Overview
This is a methodology-only skill for building CLI harnesses, with no hidden executable payloads or credential handling found.
Install this only when you want an agent to create or change CLI harness files in a target project and run local validation commands. Review generated code and tests before using them on important repositories, especially when the harness wraps real software backends.
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.
Static analysis
No suspicious patterns detected.