x.comthreadDan Kornas (@DanKornas) on X
NuGuard is an open-source AI application safety and security toolkit for agentic AI systems, released under Apache 2.0. It unifies AI-SBOM generation, structural static analysis of the AI stack, and sandboxed adversarial red-teaming (100+ scenarios covering prompt injection, tool abuse, and data exfiltration) into a single CLI workflow, with an automated judge that scores findings by impact and provides remediation guidance.
TL;DR NuGuard is an open-source CLI toolkit that generates an AI-SBOM, runs static analysis, and red-teams agentic AI apps against 100+ adversarial scenarios.
Technologies named here
- Agentic AI applications
- NuGuard
- SBOM
Techniques named here
- Prompt Injection
- Tool abuse
- Data exfiltration
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle