Security audit
Lumos
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent and disclosed, with high-impact ClawHub staff workflows gated by explicit targets, reasons, confirmation, authentication, and audit expectations.
Install only in a ClawHub staff or developer context where these workflows are appropriate. Before using the moderation, migration, or email workflows, verify the exact target and reason, review dry-run output, and require explicit signoff; for autoreview, make sure sending code diffs to the selected review engine is acceptable for your project.
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.