Hacker News: JXavierH

New comment by JXavierH in "Valve releases Steam Controller CAD files under Creative Commons license"

JXavierH — Thu, 07 May 2026 00:37:53 +0000

I know. Long live Gabe.

New comment by JXavierH in "Nuclear receptor 4A1 linked to health effects of coffee: study"

JXavierH — Sun, 03 May 2026 17:48:47 +0000

I'm all for decaf 100%.

New comment by JXavierH in "Coffee doesn't just wake you up–a biological pathway illuminates health effects"

JXavierH — Sun, 03 May 2026 17:48:00 +0000

That's why I moved to decaf. Love coffee, caffeine doesn't like me.

New comment by JXavierH in "VS Code inserting 'Co-Authored-by Copilot' into commits regardless of usage"

JXavierH — Sun, 03 May 2026 17:42:45 +0000

Implement bad idea, but use AI. That's the MO right now.

New comment by JXavierH in "Show HN: Cq – Stack Overflow for AI coding agents"

JXavierH — Thu, 26 Mar 2026 19:32:11 +0000

Yes, I agree. I've been thinking about this problem within large orgs, code search, standards and how to surface them to developer agents. This looks quite promising.

New comment by JXavierH in "Artisanal software in the age of AI codegen"

JXavierH — Thu, 26 Mar 2026 19:28:56 +0000

I think there will always be people interested in the craft. Look at photography, there's loads of digital cameras that are technically better than any old 35mm film, but people still to that for the love of the craft.

Some developers will do the same. To each their own.

New comment by JXavierH in "Show HN: Vectimus – Cedar policy enforcement for AI coding agents"

JXavierH — Thu, 26 Mar 2026 19:19:17 +0000

Vectimus does input inspection on approved MCP servers, but it can only catch known bad patterns too. It does not try to solve prompt injections or if a legitimate MCP server was comprimised and returned poisoned outputs. I do plan to add additional post took hooks in future that can scan the MCP server output too.

You're project is interesting. It's a bit of an MCP proxy in a way, moreso than Azure API Management, yours seems to give more functionality. I will definitely take a look.

Show HN: Vectimus – Cedar policy enforcement for AI coding agents

JXavierH — Thu, 26 Mar 2026 00:34:03 +0000

Hey HN. I built Vectimus because coding agents keep doing things they shouldn't and there's no runtime governance layer for the developer workstation.

The problem: Claude Code, Cursor, Gemini CLI and GitHub Copilot let agents execute shell commands, write files and call MCP servers. Most developers disable the permission prompts because they slow you down. But that means the agent can rm -rf /, read your .env, push to production or call a compromised MCP server with nothing watching.

Vectimus intercepts every tool call and evaluates it against 78 Cedar policies containing 369 rules before execution. Cedar is the policy language AWS chose for AgentCore Policy (GA this month). Evaluation runs locally via a persistent daemon in under 10ms. Zero network calls. Zero telemetry. Every evaluation produces an Ed25519-signed receipt so you have cryptographic proof of what was allowed and denied.

Every policy maps to a real incident. CVE-2025-6514 compromised 437,000+ developer environments through a malicious MCP OAuth proxy. The GitHub MCP server was hijacked via a crafted issue to exfiltrate private repo data. A Terraform agent destroyed production infrastructure. These happened.

How it hooks in: Claude Code intercepts shell commands, file writes, MCP calls and web fetches. Cursor governs shell commands, file reads/writes and MCP tool calls at the editor level. Copilot intercepts terminal commands, file edits, deletes and git pushes. Gemini CLI uses Gemini's native hook system. MCP servers are blocked by default and allowlisted per-project with input inspection. Observe mode lets you see what would be blocked before you enforce.

I also built Sentinel (https://github.com/vectimus/sentinel), a three-agent pipeline that scans for new agentic AI security incidents daily, drafts Cedar policies, replays the incident in a sandbox to prove the policy catches it, then opens a PR. The pipeline is governed by Vectimus. Every finding and policy draft is public.

All 10 OWASP Agentic Top 10 categories covered. Compliance annotations for SOC 2, NIST AI RMF, NIST CSF 2.0, EU AI Act, ISO 27001, CIS Controls and SLSA. Apache 2.0. Solo founder, built in Ireland.

Happy to go deep on the Cedar policy design, the hook architecture, the signed receipts or the OWASP mapping.

Comments URL: https://news.ycombinator.com/item?id=47525283

Points: 3

# Comments: 2