I submitted a remote code execution to the browser-use about 40 days ago. GHSA-r2x7-6hq9-qp7v I am a bit stunned by the lack of response. Any safety concerns in this project?
Show HN: Browser Harness – Gives LLM freedom to complete any browser task
21–30 of 77 posts
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#222. Can you publish a tabular comparison on your README?
3. What information gets sent to your API server?
I'm struggling to see why I should use this over agent-browser; I have not yet run into the "cross origin iframes" problem. Is this more for the 'claw crowd?
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#23Earlier quoted context omitted.
PW is usually easier to detect. Using raw CDP is in our opinion much better for this.
We published a survey of stealth browsers just yesterday https://botforensics.com/blog/stealth-browser-survey-april-2... There's still plenty that Browser-Use could improve in terms of stealthiness. We didn't detect it using CDP (good!) but can still detect that it is Browser-Use.
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#24Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#25I submitted a remote code execution to the browser-use about 40 days ago. GHSA-r2x7-6hq9-qp7v I am a bit stunned by the lack of response. Any safety concerns in this project?
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#26I was wondering when someone would finally build this. Anyway, of course this will be superseded by a harness that provides freedom to complete any task within the OS.
Unless it would be airgapped no internet access machine with just monitor I.e.
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#27Sawyer Hood's dev-browser[0] allows the browser to write playwright JS code directly. Do you have cases where his approach fails and yours works? [0] https://github.com/SawyerHood/dev-browser
PW is usually easier to detect. Using raw CDP is in our opinion much better for this.
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#28I submitted a remote code execution to the browser-use about 40 days ago. GHSA-r2x7-6hq9-qp7v I am a bit stunned by the lack of response. Any safety concerns in this project?
Hey! Where did you submit this exactly? Can you provide a link? Will ask others on the team also, but I am not sure what you are referring to.
Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#29Earlier quoted context omitted.
IIUC the point is that the agent has the ability to modify itself? So one possible term could be "self-evolving" or "self-modifying agent".
Any agent that accepts "work in this working directory" (which AFAIK, all of them do) have had this ability, even the initial GPT2/3 experiments around matching LLMs with primitive tool-calling.
s/has the ability to/is meant to
Then again, I don't think your statement is entirely correct: It assumes you've given the agent the permission to edit his source autonomously, which would normally seem unusual for an agent that's just supposed to connect to the browser.Re: Show HN: Browser Harness – Gives LLM freedom to complete any browser task
#30> Set up https://github.com/browser-use/browser-harness for me.
> Read `install.md` first to install and connect this repo to my real browser. Then read `SKILL.md` for normal usage. Always read `helpers.py` because that is where the functions are. When you open a setup or verification tab, activate it so I can see the active browser tab. After it is installed, open this repository in my browser and, if I am logged in to GitHub, ask me whether you should star it for me as a quick demo that the interaction works — only click the star if I say yes. If I am not logged in, just go to browser-use.com.
Is the the new "curl {url} | sh"?