Red Sift
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent ClawHub developer and moderation workflows with disclosed high-impact actions that require explicit user or staff operation.
Install only if you are maintaining ClawHub or a similar Convex/OpenClaw project. Review the moderation and autoreview workflows before use, because they can make authenticated platform changes or run nested review commands with broad local authority when explicitly invoked.
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.