Security audit
mcp-best-practices
Security checks across malware telemetry and agentic risk
Overview
This skill is a static MCP best-practices reference and does not add executable behavior or request unusual access.
This appears safe to install as a reference skill. Users should still treat its package/version and standards guidance as technical advice to verify against current MCP documentation before production use.
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
50/50 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.