Lobster Agent Summary
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts appear to be disclosed, purpose-aligned developer and maintainer workflows with no evidence of hidden or malicious behavior.
Install only if you need ClawHub/Convex maintainer workflows and are comfortable with tools that can run local CLI commands and, when explicitly invoked, affect authenticated services such as GitHub, Convex, or ClawHub moderation state. Review commands before confirming high-impact actions like bans, role changes, migrations, publishing proof, or deployment-related steps.
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.