Security audit
Compound Interest
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent operational guidance for ClawHub, with clean scanner telemetry and no evidence of hidden execution or data theft.
Install only if you expect ClawHub-specific staff, Convex, or repository-maintenance workflows. Review commands before approving writes, production migrations, emails, role changes, bans, or external review runs that may send code context to a model provider.
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.