A2A Hub
Security checks across malware telemetry and agentic risk
Overview
This documentation-only skill matches its stated A2A hub purpose, with credential and message-relay behavior disclosed and proportionate.
Before installing, understand that messages sent through the hub may be relayed to remote agents, and any upstream API key you provide can be used by the hub to call your registered endpoint. Use dedicated, revocable credentials and avoid sending private data or secrets to agents you do not trust.
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
59/59 vendors flagged this skill as clean.