Security audit
Intention Engine
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill that helps an agent infer user intent and challenge unclear work, with no executable code or hidden install behavior found.
Install this if you want your agent to be more proactive about inferring goals and questioning unclear or misaligned tasks. Keep user profile and memory context accurate, and be explicit when you want literal execution without broader intent inference.
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.
Static analysis
No suspicious patterns detected.