Security audit
Newton Perspective
Security checks across malware telemetry and agentic risk
Overview
No concrete harmful behavior was shown, but the target skill artifact was not available for direct review here.
This is a low-confidence benign result because the scanner signals are clean or pending, but the actual target skill contents were not available for direct inspection. Before installing in a sensitive environment, review the skill files for declared permissions, install commands, credential handling, network access, filesystem writes, and any persistence behavior.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.