AI Agents Now Open Pull Requests Faster Than Teams Can Review Them Purple Hooks Puts the Security Check Inside the Agent

Phoenix Purple Hook scans what Claude Code, Cursor, and Codex try to push and hands to the agent the fix before vulnerable code reaches a human reviewer

AUSTIN, TX, UNITED STATES, October 29, 2026 /EINPresswire.com/ — Engineering organizations that build software with AI coding assistants pay twice for each security finding. The first bill arrives in reviewer hours, when vulnerable code lands in a pull request. The second comes in rework and model tokens, when someone relays the finding back to an assistant that has long since lost the context. Phoenix Security today announced general availability of Purple Hook, which moves the security check into the coding session.
Purple Hook is a small local check that runs inside the AI coding assistant a developer already uses. It keeps Phoenix’s copy of the branch current and scans in the background after a push and when a pull request is opened. Results go straight back to the assistant, with each finding including the file, line, severity, and remedy, and the assistant fixes the code while the change is still open. The engineer sees what ran and why it blocked.
Where the cost lands
Most organizations scan at the pull request, in CI, or on a schedule. All of those run after the assistant has finished. A reviewer triages the result, an engineer pastes the finding into a fresh session, and the assistant reads through the repository again to find the code and work out a fix. That costs time and tokens at every step.
There’s also a trust cost. Engineers switch off checks that block without saying why, or quietly route around them.

What Purple Hook changes
The check runs where the work is happening. At the start of a session, the hook asks Phoenix to fetch the branch. After a push, it starts a scan and returns a ticket; the assistant continues, and the result appears in the session on the assistant’s next action. Commits aren’t scanned, and pushes aren’t held up. Opening a pull request triggers a scan of the whole branch against main, and the organization’s policy decides whether it blocks, warns, or goes through.
Findings arrive ready to fix. Phoenix’s knowledge graph of the codebase maps files, functions, calls, and imports, so the assistant goes straight to the fix. Only findings in the changed lines can block. The system judges a ten-line change on those ten lines, regardless of what else sits in the backlog. Notices have a fixed size and state how many more findings exist, so a big result does not swamp the session. Administrators can switch on AI-suggested fixes, which are labeled as suggestions and cannot remove a finding or change a verdict.
The hook also shows its work. Each answer separates findings that block from those worth fixing and those waived. When a scan is skipped or incomplete, the answer says so and gives the reason. Security teams set an organization-wide floor that individual workspaces may tighten, and the Enforcement page shows which repositories have the check installed and which have gone quiet. Phoenix’s server-side pull request check stays on as the enforced layer, so a repository without the hook is still gated.

Phil Moroni
Phoenix Security
+1 919-594-8888
Visit us on social media:
LinkedIn
Instagram
Facebook
YouTube
X

Media gallery