Security audit
roundtable-discussion
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill materials are coherent developer and maintainer workflows with disclosed command, network, auth, and moderation use, and no artifact-backed malicious behavior was found.
Install only if you intend to use ClawHub/Convex developer or maintainer workflows. Review privileged actions before running them, especially moderation commands, GitHub operations, Convex deploy/dev commands, and the autoreview helper's full-access review mode.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.