Agent Sightings Real agent use cases

Find a Linux vulnerability hidden for 23 years

As described in the source, nicholas Carlini, a research scientist at Anthropic, ran a short script that looped over every file in the Linux kernel source. For each file, it told Claude Code it was in a CTF, hinted the bug was in that file, and asked it to write its most serious finding to an output directory. Claude Opus 4.

Agent or tool
Claude Code
Topic
Software Development
Reported on
Hacker News
Added
2026-10-15

Why it matters

Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 106 sightings filed under Software Development on Agent Sightings (number 40 by interest), and one of 164 involving Claude Code.

How you could try it

Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Claude Code or any similar agent and adjust the details to your situation.

In this repo, find a Linux vulnerability hidden for 23 years. Read relevant code, apply a minimal patch, run available checks, and summarize the diff. Stop before merge or deploy.

The prompt breaks down into 3 steps you can check as the agent works:

  1. In this repo, find a Linux vulnerability hidden for 23 years.
  2. Read relevant code, apply a minimal patch, run available checks, and summarize the diff.
  3. Stop before merge or deploy.

Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.

Source

Read the original first-hand account on Hacker News: https://news.ycombinator.com/item?id=47633855. Our summary is a paraphrase; details are in the source.

Featured in these guides

Related sightings

← All 991 use cases