openlayers
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed ClawHub development and moderation helper set with powerful but explicit workflows, not hidden malware-like behavior.
Install this only in a ClawHub maintainer or developer context. Treat moderation, role-change, PR-commenting, publishing, and full-access review commands as powerful actions: confirm exact targets, keep tokens scoped, and review commands before allowing writes.
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
65/65 vendors flagged this skill as clean.