Security audit
Best Practices
Security checks across malware telemetry and agentic risk
Overview
The skill is a disclosed ClawHub operator workflow with high-impact moderation powers, but its instructions are scoped, user-directed, and include confirmation and verification steps.
Install or enable this only for trusted ClawHub staff or maintainer contexts. Treat ban, unban, role-change, report-triage, and proof-publishing commands as privileged actions: confirm the target and reason, use the least-privileged token available, and verify the resulting state after each write.
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.