Knowledge to ClawHub Skill Publisher
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only workflow skill for documenting and publishing reusable ClawHub skills, with the main caution being to review content before publishing or syncing persistent knowledge.
Safe to install as a workflow helper. Before running any publish or memory-sync step, review the generated skill folder, remove secrets or raw conversations, and confirm the intended ClawHub account, slug, version, and files.
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
65/65 vendors flagged this skill as clean.