Information Extraction
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent local information-extraction helper that processes user-provided text into structured outputs without evidence of hidden access, network activity, persistence, or destructive behavior.
Reasonable to install for local text extraction. Be aware that extracted entities, evidence snippets, and triples may be written to local output files you choose, so avoid processing sensitive documents unless you are comfortable with those structured outputs being saved.
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
64/64 vendors flagged this skill as clean.