Google Sheets
Security checks across malware telemetry and agentic risk
Overview
The inspected artifacts are coherent ClawHub development and workflow materials with no concrete evidence of hidden, destructive, or exfiltrating behavior.
Install or use this only in a ClawHub development or maintainer context. Be aware that some repo-local workflows can run tests, invoke GitHub or Convex tooling, and perform staff moderation actions when explicitly directed, so use the relevant credentials and confirmation prompts carefully.
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
59/59 vendors flagged this skill as clean.