Security audit
Llm Evaluation
Security checks across malware telemetry and agentic risk
Overview
This is a plain Markdown guidance skill for LLM evaluation and does not contain code, install hooks, credential access, persistence, or hidden behavior.
This appears safe to install as a planning guide. When applying it to real evaluation work, handle production examples, PII, high-stakes review data, and release decisions according to your organization's privacy and approval policies.
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
53/53 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.