FireClaw – Open-source proxy defending AI agents from prompt injection
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…
FireClaw – Open-source proxy defending AI agents from prompt injection launched on March 17, 2026 with 5 votes, #1,928 of 23,380 launches that month and more than 75% of that year's launches.
What it does
🛡️ A firewall for your agent's brain. Open-source security proxy that protects AI agents from prompt injection attacks. 4-stage pipeline, community threat feed, no bypass mode. - raiph-ai/fireclaw
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
/agent by Firecrawl Dec 2025 · firecrawl.dev · ▲569While building mendable - we found that feeding LLMs well-structured markdown improved accuracy. We also found it surprisingly hard. We found some great tools online, but none reliably handled the entire process. We wanted an API that took a URL, crawled the pages in the URL, and gave us an easy-to-use, up-to-date markdown we could feed into our index. So, we released an open-source repo and an API that crawls and turns entire websites into a markdown with just a few lines of code The API handles: - Crawling without consistent sitemaps - Infra to handle running many crawling jobs - Proxying,…
The new Firecrawl /searchJul 2026 · docs.firecrawl.dev · ▲257Our most accurate Search API for AI agents.
Agent Browser ShieldJun 2026 · github.com · ▲109I've been experimenting with Claude Code, ChatGPT Agent, and OpenClaw to perform more open-ended tasks for me online. A big blocker I've hit on shopping and research tasks is the agent getting a key piece of info wrong. For example, in one case, my agent decided to add a brand I don't like to the cart because the site flagged it as almost sold out The HN crowd is probably pretty aware of the threats and can avoid them while browsing. But what about their agents? I tried prompting, but it was ineffective, because once the AI saw the threat, it polluted/distracted its context Looking at…
Firecrawl CLIMar 2026 · docs.firecrawl.dev · ▲249Firecrawl skills are an easy way for AI agents such as Codex, Claude Code, Cursor, and OpenCode to use Firecrawl through the CLI.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
