Security audit
Mentionkit Skill
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent developer and ClawHub operations workflows with disclosed command use and user-confirmation gates for high-impact actions.
Install only if you want these agent workflows to guide local development and ClawHub staff operations. Be especially careful with the moderation, content-rights, and migration skills: they can guide authenticated production-impacting commands, so use them only with the intended ClawHub admin access and preserve their confirmation, dry-run, and audit-log steps.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.