AANA Human Review Router Skill
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill adds human review gates for sensitive or high-impact actions and does not show hidden code execution or credential use.
Install this if you want the agent to pause for approval or route sensitive decisions to trusted reviewers. Expect extra friction on financial, legal, medical, production, deletion, publishing, or other high-impact tasks, and only connect it to review channels you trust because redacted task summaries may be shared there.
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.