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 next. 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 next. Gelei Deng and … More
The post PentestGPT: Open-source automated penetration testing agentic framework appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
AI deployments are stretching enterprise security to its limits
Citrix expands Platform Flex with observability and secure developer services
GPT-5.6-Cyber refuses security researchers’ requests far less often