Security audit
Write A Skill
Security checks across malware telemetry and agentic risk
Overview
The artifacts appear to be a coherent ClawHub maintainer skill set with disclosed admin, Convex, documentation, and review workflows guarded by auth, dry-run, and confirmation requirements.
Install only if you are working on ClawHub or Convex maintainer workflows and are comfortable with agent-guided admin operations. Review commands before approving them, especially moderation, production migration, email-send, and external-model review flows.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.