Agentsop Cost Tiered Models
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill that guides agents on choosing cheaper or stronger language models for different workflow steps, with no executable behavior or hidden access.
Reasonable to install if you want guidance on splitting expensive and cheap model calls. Treat its model and benchmark examples as dated planning advice, and re-measure cost and quality on your own workflow before relying on its recommendations.
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.