Llm As Judge
Security checks across malware telemetry and agentic risk
Overview
This is a coherent LLM evaluation guide that discloses its use of the user's own LLM API keys and shows no hidden execution, persistence, or unrelated data access.
Install only if you are comfortable sending sampled evaluation data to your selected LLM providers and paying for those calls. Use scoped or budget-limited API keys, configure sampling and promotion-gate behavior deliberately, and avoid evaluating confidential data unless provider terms and logging practices are acceptable.
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.