Security audit
GetProspect
Security checks across malware telemetry and agentic risk
Overview
The inspected artifacts describe legitimate ClawHub and Convex workflow skills with disclosed commands and confirmation gates, and the supplied scanners found no malware indicators.
Install only if you intentionally want these ClawHub/Convex operational skills available to your agent. Review the admin, email, migration, and autoreview sections first, because they can guide real account, production data, or external-reviewer actions when you explicitly ask for them.
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
61/61 vendors flagged this skill as clean.