Security audit
Arrive Guideline Architect
Security checks across malware telemetry and agentic risk
Overview
This skill is not malware-like, but it makes stronger animal-research compliance and sample-size claims than its code supports.
Treat this as a drafting/checklist aid only. Do not rely on it for statistical power, ARRIVE compliance, IACUC readiness, or animal-welfare decisions without review by a qualified biostatistician and institutional ethics reviewer. Run it in a dedicated folder and choose output filenames carefully.
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.
Static analysis
No suspicious patterns detected.