Back Feeds2.Feedburner

PentestGPT: Open

Feeds2.Feedburner •Anamarija Pogorelec • August 12, 2026

PentestGPT is an open-source penetration testing agent that points a large language model at a target and lets it work. In its default mode it runs recon, then exploit, then walkthrough, each stage feeding the . Switch it to pentest mode and the stages become asset discovery, vulnerability identification, report. No human sits in the loop. The agent drives Claude Code or Codex, runs the tools, and decides what to try . Gelei Deng and … More →

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

PentestGPT Launches as Autonomous Penetration Testing Framework PentestGPT has been released as an open-source penetration testing framework that automates the entire process of reconnaissance, exploitation, and reporting. It utilizes advanced language models, Claude Code and Codex, to operate without human intervention. The framework allows for asset discovery, vulnerability identification, and report generation, effectively functioning as an autonomous pentester. This development could significantly impact cybersecurity practices by enabling faster and more efficient penetration testing. However, the lack of human oversight raises concerns about the potential misuse of such technology. The current status of PentestGPT is that it is publicly available for use. 2 sources 37

Extracted Entities

Tools (2)

Claude Code Codex