ashwinr2002

ashwinr2002 on Hacker News

Re:Claude Code Found a Linux Vulnerability Hidden for 23 Years on Saturday April 04, 2026 @06:52PM (#47644366)

Prompt Injections are very very rare these days after the Opus 4.6 update

Re:Let's discuss sandbox isolation on Saturday February 28, 2026 @05:01PM (#47200758)

This is unreachable?

Re:An AI Agent Published a Hit Piece on Me on Thursday February 12, 2026 @05:47PM (#46996365)

minger's a new word

Re:Claude Code Is Being Dumbed Down on Thursday February 12, 2026 @12:16AM (#46985139)

This is a horrible change! I agree with everything in the article

Show HN: Dangerously-skip-permissions IFF it doesn't WRITE outside Sandbox

Posted by ashwinr2002 on Friday February 06, 2026 @01:48AM
from the show-hn dept.

https://github.com/ContextFort-AI/Runtime-Controls

Permission prompts are noisy if a command’s damage radius is limited to a sandbox.I wanted to be asked for approval iff it’d make changes in external environments or talk to a network.I built a Claude Code plugin that: (https://postimg.cc/crvWLNRR)1) Always prompts for “write-external” commands (db updates, API calls, remote writes), e.g. scp, curl -X POST, git push, sqlite3 etc. 2) Blocks...

( Read More... | no comments | on HN )

Re:Show HN: Prompt-injection firewall for OpenClaw agents on Monday February 02, 2026 @11:26AM (#46857880)

Apologies for the formatting

Can we not assume that the plan you just said “ok” to came from a user prompts you made earlier in the chat session and hence does influence this decision process.

Another point in the idea is that this trusted context can include even the AI replies up until there hasnt been a tool calls yet that brings back a response an attacker can control

But it’s entirely possible that there are edge cases here, a red teaming dataset to cover these cases shouldn’t be hard to create

Show HN: Prompt-injection firewall for OpenClaw agents

Posted by ashwinr2002 on Monday February 02, 2026 @06:33AM
from the show-hn dept.

https://github.com/ContextFort-AI/clawdbot-runtime-controls

People seem to be blindly hooking up their OpenClaw’s to their personal data. So, I built runtime controls to prevent at the least, very simple prompt injection attacks.Once installed, it hooks to Node.js child_process module in the gateway process and listens to tool calls and their response streams. And a fetch hook to monitor user prompts (both could’ve been through fetch, happy to discuss...

( Read More... | 3 comments | 3 points | on HN )

Re:Using Proxies to Hide Secrets from Claude Code on Thursday January 22, 2026 @10:21PM (#46727980)

I understand that, but how do you come up with the endpoints you want claude to have access to ahead of time?

For example, how do you collect all the endpoints that have access to customer info per your example.

Thought about it and couldn't find a way how

Re:Using Proxies to Hide Secrets from Claude Code on Tuesday January 20, 2026 @07:58PM (#46699868)

> With macaroons you can design the authz scheme that you want for any arbitrary API.

How would you build such an authz scheme? When claude asks permissions to access a new endpoint, if the user allows it, then reissue the macaroons?

Re:Using Proxies to Hide Secrets from Claude Code on Tuesday January 20, 2026 @07:40PM (#46699738)

This seems like an under-rated comment. You are right, this is a vulnerability and the blog doesn't talk about this.

Re:Show HN: Visibility and Controls for Browser Agents (ContextFort YC... on Wednesday January 14, 2026 @04:23AM (#46614026)

P.S.: The extension has as many permissions as Claude in Chrome itself. But, the only network requests from the extension are to posthog, just for us to know which features are being used.

Here is a youtube video where I show the network requests of the extension: https://www.youtube.com/watch?v=J356Nquxmp4

To know what posthog collects and how to disable it (change in a single line of code), please refer to this file: https://github.com/ContextFort-AI/ContextFort/blob/main/POST...

Show HN: Visibility and Controls for Browser Agents (ContextFort YC S25)

Posted by ashwinr2002 on Wednesday January 14, 2026 @04:22AM
from the show-hn dept.

https://contextfort.ai/

Hey HN! I’m Ashwin, co-founder of ContextFort (https://contextfort.ai/). We provide visibility and controls for AI browser agents like Claude in Chrome through an open-source browser extension.Browser agents are AI copilots that can autonomously navigate and take actions in your browser. They show up as standalone browsers (Comet, Atlas) or Chrome extensions (Claude).They’re especially useful...

( Read More... | 1 comment | on HN )

Re:Show HN: April (YC S25) – Hit Inbox Zero with Just Your Voice While... on Friday August 15, 2025 @06:14PM (#44917889)

Really cool product! Which email providers do you support?