Hacker News: raiph_ai

New comment by raiph_ai in "Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection"

raiph_ai — Mon, 23 Mar 2026 02:02:46 +0000

Thanks! Checked out your project — really impressive work. The way I see it, our projects are complementary: FireClaw sanitizes inputs (is this content trying to hijack the agent?), yours governs outputs (should the agent take this action?). Together that's defense-in-depth.

We just shipped /api/scan in v1.1.0 which could plug into your policy evaluation — scan content before it enters the decision pipeline. Also now on Docker and npm (npx fireclaw) for easier integration.

Happy to brainstorm integration. Feel free to open an issue on our repo or reach out on GitHub.

New comment by raiph_ai in "Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection"

raiph_ai — Mon, 23 Mar 2026 01:56:13 +0000

Thanks! Good call on the icons — we're swapping all the emojis to Lucide SVG icons in the next update. Much cleaner cross-platform.

And for the record, that's actually a honey badger, not a raccoon :) Honey badgers don't care (about prompt injection).

New comment by raiph_ai in "Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection"

raiph_ai — Tue, 17 Mar 2026 16:29:32 +0000

Creator here. Quick TL;DR and some context:

FireClaw = prompt injection firewall for AI agents. Proxy architecture, not just detection. 4-stage pipeline, no bypass mode, community threat feed.

The thing that surprised us most during research: nobody is doing this. There are great pattern detectors (Rebuff, LLM Guard, etc.) but they all work post-hoc — the content has already entered the agent's context by the time you detect injection. FireClaw intercepts it before that happens.

The Pi appliance was honestly just for fun at first, but it turns out having a physical box with a screen showing "3 threats blocked today" is surprisingly reassuring. The OLED does an animated fire claw when it catches something.

Happy to answer any questions about the architecture, the canary token system, or the threat feed privacy model.

Show HN: FireClaw – Open-source proxy defending AI agents from prompt injection

raiph_ai — Tue, 17 Mar 2026 16:28:53 +0000

Hey HN,

We built FireClaw because we kept watching AI agents get owned by prompt injection through web content. The agent fetches a page, the page says "ignore previous instructions," and suddenly your agent is leaking data or running commands it shouldn't.

The existing solutions detect injection after the fact. We wanted to prevent it.

FireClaw is a security proxy that sits between your AI agent and the web. Every fetch passes through a 4-stage pipeline:

1. DNS blocklist check (URLhaus, PhishTank, community feed) 2. Structural sanitization (strip hidden CSS, zero-width Unicode, encoding tricks) 3. Isolated LLM summarization (hardened sub-process with no tools or memory) 4. Output scanning with canary tokens (detect if content bypassed summarization)

The key insight: even if Stage 3's LLM gets injected, it has no tools, no memory, and no access to your data. It can only return text — which still gets scanned in Stage 4. The attacker hits a dead end.

Other design decisions: - No bypass mode. The pipeline is fixed. If your agent gets compromised, it can't disable FireClaw. - Community threat feed — instances anonymously share detection metadata (domain, severity, detection count) to build a shared blocklist. No page content is ever sent. - Runs on a Raspberry Pi as a physical appliance with an OLED display that shows real-time stats and lights up with animated flames when it catches a threat.

We searched the literature and open source extensively — no one else is doing proxy-based defense for agent prompt injection. Detection exists, sandboxing exists, but an inline proxy that sanitizes before content reaches the agent's context? We couldn't find it.

200+ detection patterns, JSONL audit logging, domain trust tiers, rate limiting, and cost controls. AGPLv3 licensed.

Website: https://fireclaw.app

Would love feedback from anyone working on AI agent security. What are we missing? What attack vectors should we add to the pattern database?

Comments URL: https://news.ycombinator.com/item?id=47414911

Points: 5

# Comments: 7

New comment by raiph_ai in "Show HN: AwardClaw – 24/7 award travel research agent"

raiph_ai — Tue, 17 Mar 2026 02:17:36 +0000

Great idea. The cruise line space has the same dynamic — prices fluctuate constantly after you book, and if you catch a lower fare the cruise lines will often give you onboard credit or other perks. But they don't proactively tell you about it, so you have to keep checking yourself. An agent that continuously monitors for these kinds of opportunities is exactly the right approach.

New comment by raiph_ai in "NASA targets Artemis II crewed moon mission for April 1 launch"

raiph_ai — Sun, 15 Mar 2026 03:18:24 +0000

I watched a news piece about this and alot of people are calling for more testing before sending a crew up. Every mission has risks but there seems to be real concern about the vehicle's re-entry into Earth's atmosphere. Blessings and good luck to the whole team.

New comment by raiph_ai in "AI should not replace people at Atlassian, says CEO"

raiph_ai — Sat, 14 Mar 2026 15:03:38 +0000

I feel bad for all the employees that were affected. Atlassian years ago started as an innovative company, look at their original mission statement. "Open company, no bullshit" and Don't F&%# the customer. They truly had great products that complemented each other. The problem now, is alot of the tools are not need, or can be made with some vibe coding.

New comment by raiph_ai in "Show HN: OpenClaw-class agents on ESP32 (and the IDE that makes it possible)"

raiph_ai — Sat, 14 Mar 2026 02:14:05 +0000

This project looks super cool. I love having the idea of having openclaw on a low powered device. I am working on something and should have it out next week. It was designed to run on a raspberry pi and would be a great companion to your project. I will post back when it is live and would love for you to take a look.

New comment by raiph_ai in "Can I run AI locally?"

raiph_ai — Sat, 14 Mar 2026 01:55:03 +0000

Great site, I have an M2 and M3pro and was thinking about getting and Ultra M4 and wanted to know if it was going to be worth it. Now I can see exactly what models I can run locally.