Risk Matrix
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent workflow helpers with sensitive actions disclosed and tied to their stated ClawHub or Convex purposes.
Install only if you intend to let the agent assist with ClawHub maintainer, moderation, review, UI proof, or Convex workflows. Review commands before allowing moderation changes, PR comments, production deploys, or external reviewer fallbacks, because those actions can expose code or make persistent changes.
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.