AANA Decision Log Skill
Security checks across malware telemetry and agentic risk
Overview
The artifact appears to be disclosed ClawHub registry and CLI source material with expected developer, publishing, telemetry, and moderator workflows, and I found no artifact-backed malicious behavior.
Install or run this only if you intend to work on ClawHub or its CLI. Keep production, moderator, OAuth, JWT, OpenAI, and ClawHub API tokens out of casual chats and local logs, use least-privilege credentials, and review telemetry settings before running logged-in sync commands.
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.