AOI Prompt Injection Sentinel
Security checks across malware telemetry and agentic risk
Overview
This skill is a local text scanner that checks user-provided text for prompt-injection patterns and does not show hidden network, file-writing, credential, or persistence behavior.
This appears safe to install for local prompt-injection screening. Treat it as a lightweight heuristic scanner, not a complete security boundary, and avoid sharing its JSON output externally if the analyzed input contains sensitive text.
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.