Security audit
AIsa Youtube Search
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts are coherent ClawHub and Convex workflow helpers that disclose their higher-impact commands and do not show hidden exfiltration, persistence, or destructive behavior outside their stated purposes.
Install these skills only for agents you expect to perform ClawHub/Convex maintainer work. Review sensitive commands before use, keep GitHub/ClawHub/Convex tokens least-privileged, use dry-run modes where available, and consider the autoreview --no-yolo option if nested full-access review is not appropriate.
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
49/49 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.