Skilled Models Advisor
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward model-selection advisor that tells the agent to query a dedicated model database or sub-agent before recommending AI models and costs.
Before installing, understand that the skill may cause your agent to send model-selection questions and workload estimates to the tool-models sub-agent or its local CLI. That is expected for this skill, but avoid including unnecessary sensitive business details in those prompts.
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.