{"slug": "show-hn-a-firewall-for-ai-agents-with-auditing", "title": "Show HN: A Firewall for AI agents with auditing", "summary": "A developer built a firewall for AI agents in Rust that runs under five milliseconds, using a DAG to plan and enforce actions, track tool calls and data flow, and flag out-of-context reads. The tool addresses security concerns with agent-based systems by avoiding the hallucination and latency issues of LLM-based guards.", "body_md": "Hi all,\n\nAs there are more and more agents in the internet; Security is going to be a big problem. Currently, the problem is solved using a LLM to guard Agent but this creates the problem of hallucination and latency, so I coded a firewall in rust that runs under five miliseconds. This works by creating a plan and enforcing the plan; for per action call, this enforces using the Model context protocols list and for sequence it tracks every single tool call and data flow; there is also a taint mechanism where if the agent reads something outside of the user context, it flags and adds more security mechanism. It works by using a DAG.\n\nComments URL: [https://news.ycombinator.com/item?id=48726867](https://news.ycombinator.com/item?id=48726867)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-a-firewall-for-ai-agents-with-auditing", "canonical_source": "https://github.com/beebeeVB/trajeckt/", "published_at": "2026-06-29 23:52:48+00:00", "updated_at": "2026-06-30 00:21:14.145045+00:00", "lang": "en", "topics": ["ai-agents", "ai-safety", "ai-tools", "ai-infrastructure"], "entities": ["Rust"], "alternates": {"html": "https://wpnews.pro/news/show-hn-a-firewall-for-ai-agents-with-auditing", "markdown": "https://wpnews.pro/news/show-hn-a-firewall-for-ai-agents-with-auditing.md", "text": "https://wpnews.pro/news/show-hn-a-firewall-for-ai-agents-with-auditing.txt", "jsonld": "https://wpnews.pro/news/show-hn-a-firewall-for-ai-agents-with-auditing.jsonld"}}