Security audit
Agent Input Firewall
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple prompt-injection scanning helper that discloses sending selected untrusted text to a named external endpoint.
Before installing, be aware that any text you choose to scan will be sent to the publisher's external service, and future use may involve x402 payment. Avoid sending secrets or private content unless you trust the service and its data-handling claims.
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.