OADP Agent Discovery
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is coherently designed for public agent-hub discovery, with active sharing gated by explicit configuration.
Install only if you want your agent to make public web and DNS discovery requests. Keep trusted_hubs empty for passive-only use, enable federation intentionally, verify hubs manually before trusting them, and use the lowest privacy tier that fits your workflow.
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
63/63 vendors flagged this skill as clean.