AANA Agent Memory Gate Skill
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is a coherent memory-safety guide that asks agents to get user approval before storing, changing, deleting, importing, exporting, or sensitively reusing memory.
Reasonable to install if you want stricter controls around agent memory. Before enabling any platform permissions, verify that the unrelated marketplace capability tags do not grant real purchase or crypto authority, and only configure an external AANA checker if you trust it and keep payloads redacted.
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
62/62 vendors flagged this skill as clean.