Security audit
Amoeba Management Analysis
Security checks across malware telemetry and agentic risk
Overview
The available evidence shows a coherent ClawHub/Convex agent-skill bundle with disclosed development and moderation workflows, and no supported indication of malicious behavior.
Install this only in a ClawHub maintainer/development context. Be aware that some workflows can run local tooling, invoke external review CLIs, use authenticated GitHub or ClawHub access, publish PR proof comments, or perform moderation actions when directed.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.