Security audit
AI Risk Assessment
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts describe purpose-aligned development, moderation, review, and Convex workflows without hidden persistence or unrelated data handling.
Install only if you expect a skill set that can run local development commands, review diffs, interact with GitHub/ClawHub/Convex tooling, and perform staff moderation when explicitly directed. Review the moderation and autoreview commands before use, especially the full-access review mode and any external reviewer fallback that may receive repository diffs.
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.