Security audit
Clawdhub Submit
Security checks across malware telemetry and agentic risk
Overview
This is a guide for publishing ClawdHub skills, with user-run troubleshooting and publishing commands but no bundled executable code or hidden automation.
Before installing or following the guide, verify the ClawdHub CLI package/source, run the example commands only in the intended skill directory, keep any login token private, and confirm the target account, slug, and path before publishing.
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.
Static analysis
No suspicious patterns detected.