AI security checks shouldn’t turn an unknown into a pass.
This is a dev post classified by Jev as Security (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
AI security checks shouldn’t turn an unknown into a pass. Guardana is an open-source AI security verification tool for teams checking model artifacts, deployed models and agents, MCP servers, and recorded traces. It helps you verify AI systems from build to production by combining offline artifact scans, bounded active probes, and recorded-run analysis in one rule engine. Key features: • Static artifact scans – offline checks for code and model artifacts, with no model or network required • Active probing – bounded checks against a deployed model, agent, or MCP server • Trace analysis – ch
Posted by Dan Kornas (99.3k followers) 2 h ago · 5 likes · 584 views · view the original post on X. Kept by the Dev Radar as Security.
More dev work like this
- Showboat is a Linux post-exploitation framework built for stealth and long-term access. — @PicusSecurity
- Auto-discovers devices using nmap and organizes them into labeled groups via a… — @tom_doerr
- Azure security gets complicated fast. — @AiswaryaVenkit1
- Here's a question I think we need to start asking when we give AI agents access to… — @shehackspurple
- 平时觉得自己隐私保护得还行？其实偶尔做一次泄露自查也挺有必要。 — @bkdgiffug
- Applications today can pull thousands of third-party packages, and AI agents are… — @depthfirstlabs
- 以前拿 Claude Code 做安全研究，很多时候还是得自己一步步引导。 — @bkdgiffug
- Useful tool for cybersecurity researchers and red teamers. — @0x0SojalSec
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23.3k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 06:46 UTC. Full method.