GraphQL
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only GraphQL guidance skill with no code, no account access, and no instructions to change or read user data.
This skill appears safe to install as a reference aid for GraphQL work. Treat its recommendations as engineering guidance and review them for fit before applying them to production APIs.
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.