Load Balancer
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent repo-maintainer and Convex workflow skills with disclosed powerful actions, not hidden or deceptive behavior.
Install or enable this only where the agent is trusted to operate on the ClawHub repo, GitHub state, Convex deployments, and moderator tooling. Pay particular attention before running the autoreview helper in its default full-access mode or any moderation/migration command, because those actions can affect local code, CI, production data, or user accounts.
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.