Novee debuts Agentic Fix, pushing pentest findings into Claude, Copilot and Cursor
Artificial intelligence penetration testing startup Novee Cyber Security Ltd. today launched Agentic Fix, a new capability that pushes validated exploit findings directly into the AI coding agents developers already use to write and patch software.
The product extends the Novee platform by generating remediation guidance from the same exploit context used to uncover a vulnerability. Then it routes that guidance to coding assistants, including Anthropic PBC’s Claude, OpenAI Group PBC’s Codex, GitHub Inc.’s Copilot, Cursor and Cognition AI Inc.’s Devin.
The release targets a bottleneck that has emerged as autonomous testing tools have shortened the time required to identify vulnerabilities. While discovery timelines have compressed from quarters to hours, triage, assignment, patching and retesting remain largely manual, leaving exploitable issues sitting in engineering backlogs.
When Novee identifies an issue, the platform now generates a detailed GitHub issue with remediation guidance tied to the specific exploit path validated against the customer’s application. The coding agent selected by the customer uses that context to produce a fix and open a pull request against the repository. Once a fix is merged, Novee reassesses the affected asset to confirm that the original vulnerability has been resolved.
