Unclecheng-li/VulnClaw
An LLM agent that runs a penetration test from a plain-language goal: recon, finding weaknesses, exploiting them, then a report. It stops once the goal is reached, and a flag only counts when it shows up in real tool output.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Security testers working on systems they have written permission to test, who want an agent to handle the repetitive steps.
Not for
Anyone testing a system without written authorization; the public page gives no license or release details, and the summary is thin.
Repo
- Stars
- None
- License
- NoneNo license means the author keeps every right. You can read the code, but you have no right to copy or reuse it.
- Maturity
- active
- Last push
- Last checked
- 2026-11-14