Agentpmt Current Clawhub Skills
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable index skill that points users to AgentPMT ClawHub pages and install commands, with credential and payment implications disclosed for the linked skills rather than handled by this skill itself.
Installing this index skill is low risk, but it routes to other AgentPMT skills, some of which may involve bearer tokens, x402 payments, or external services. Review each linked skill’s permissions, credential handling, and pricing before installing or using it.
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.