Paystack
Security checks across malware telemetry and agentic risk
Overview
The inspected skill materials are coherent with their stated developer, Convex, review, UI proof, and ClawHub moderation purposes, with no scanner or artifact evidence of malicious behavior.
Install only if you want these developer and ClawHub maintainer workflows available to your agent. Review the high-authority commands before use, especially nested full-access review, GitHub publishing/commenting, package installation, Convex deployment commands, and moderator actions such as bans, role changes, hiding, or un-hiding content.
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.