Atlas Landing Page Auditor
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only landing page audit skill with no code execution or sensitive access, though its crypto tag and DeFi upsell wording appear mismatched.
Safe to install as a lightweight CRO audit guide. Users should treat the external Atlas links and paid ZIP pack references as optional promotions, and maintainers should clean up the misleading crypto tag and DeFi wording to reduce confusion.
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
65/65 vendors flagged this skill as clean.