Open Ontologies
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed ontology-building helper that runs through an external MCP server and only describes purpose-aligned local processing, optional user-directed network actions, and expected file persistence.
Install the MCP server only from the intended cargo package or GitHub release, review that external binary if handling sensitive data, and require explicit confirmation before pushing to SPARQL endpoints, applying production ontology changes, or saving/versioning sensitive datasets.
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
66/66 vendors flagged this skill as clean.