Publish To ClawHub
Security checks across malware telemetry and agentic risk
Overview
This is a transparent instruction-only skill for helping publish a local skill to ClawHub and GitHub, with appropriate safety checks around credentials and public release.
Install this if you want an agent to help prepare and publish skills. Before approving any action, review the target directory, git diff, repository, account identity, version, and changelog, and prefer browser login, SSH, or a credential manager instead of pasting long-lived tokens into chat.
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.