prompt2pwn

CLI Tool to Mount an LLM agent inside a CTF Chal Container

AI & Machine Learning Command Line Systems & Infrastructure

Explore on GitHub Read Hacker News discussions

2Distinct people

2Mentions

0Explicit recommenders

3GitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

CLI Tool to Mount an LLM agent inside a CTF Chal Container

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour2 dated mentions

Observed mentions: 2026-02-24 13:11:31 UTC to 2026-02-24 16:54:29 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions
Feb 24, 13:00	2026-02-24 13:00:00 UTC	2026-02-24 14:00:00 UTC	1	1
Feb 24, 14:00	2026-02-24 14:00:00 UTC	2026-02-24 15:00:00 UTC	0	0
Feb 24, 15:00	2026-02-24 15:00:00 UTC	2026-02-24 16:00:00 UTC	0	0
Feb 24, 16:00	2026-02-24 16:00:00 UTC	2026-02-24 17:00:00 UTC	1	1

What Hacker News says

2 sources

bigEnotation·Feb 24, 2026Submission

Show HN: Prompt2pwn – CTF Automated Solver

Tested it out this [weekend](https://ctftime.org/team/425785), spent $100 across xai ($35), google($35), anthropic($25). - xai:grok-4-1-fast-reasoning solved 8 - google:gemini-3-flash-preview solved 5 (building on xai) - anthropic:opus-4-5 couldn't solve any additional ones - also was a bit annoyed by the constant 429 ratelimiting, wished I had instead switched to openai, but I didn't want to keep spending money. Did pretty good for web and cryto, less so for pwn Built based on devcontainers.

1 points · Open discussion

wwdmaxwell·Feb 24, 2026Submission

I spent $100 benchmarking LLM providers on a weekend CTF

This past weekend, I decided to test out a cli tool I've been building to help me do source code reviews _faster_. I figured the best environment for such a tool would be a Weekend CTF event. I like web challenges since you get a nice dump of source code, as well as a Dockerfile or docker compose setup for how to run everything locally. Usually, I can complete 2-3 Web challenges before I get stuck. To help get unstuck I found myself increasingly turning to LLMs as a pairing partner. I'm a fan of devcontainers, so I figured I could apply a similar concept with an agent*, where I load the agent into a container, mount the source code, and even start up any provided Dockerfile or docker-compose.yml so that the agent can actually test real `curl` commands! So how did it go? It was pretty helpful for the web challenges. I was able to cruise th

Read the rest

rough 5 between Friday and Saturday. I decided to see how it would do in the other categories - without any input / guidance from me as I typically stick to web. In total *we* solved 19 challenges. It's best category was crypto with 4/7 solved, and it's worst was pwn with 2/5. I was also curious how different providers would fair, because this was an automated agent, I started off using xai since they were the cheapest. xai was able to solve 8 challenges autonomously with just source code and challenge descriptions. I then pivoted to gemini as the next cheapest, and it did pretty well and was able to build on xai's "analysis" and solve 5 additional challenges. I further tried to pivot to anthropic's Opus model, but it wasn't able to crack any additional challenges, and I got frustrated since I kept getting rate limited with 429 errors (so I kind of wish I switched to openai 5 instead, as it seems like Anthropic doesn't really like agents other than Claude calling their models. In terms of cost breakdown I spent $ 33.06 with xai $ 35.61 with google $ 24.04 with anthropic Bringing the total just under $100 for a weekend benchmarking exercise. Going forward I'm not really interested in paying to copy-paste CTF flags, but I did find the agent helpful for brainstorming solutions, and it worked a lot better when connected to the source code, with access to an instance running locally, and also augmented with MCP tools that allowed concept and source code searching. I'm planning to use similar concepts to build out a dev/review agent. The source code for my setup is here: https://github.com/edelauna/prompt2pwn * My initial version does require setting `--priveleged` on the Docker runtime. I originally tried to use podman, but I ran into networking / dns issues with how I wanted to make MCP tools available to the agent. Please open an issue on the repo and let me know if you have any ideas how to harden this.

1 points · Open discussion