Knowledge Graph for Agents
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only guide for adding knowledge-graph memory to an agent, with no executable installer or hidden behavior found.
Install only if you want your agent to build persistent relationship memory from indexed content. Scope the data sources carefully, avoid indexing sensitive documents unless intended, and set retention and access controls for any SQLite or Neo4j graph you create.
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
67/67 vendors flagged this skill as clean.