Phoenix Security Makes Purple Pentest Deep Generally Available to Prove Which Exploits Teams Need to Fix | Product Video

Purple Pentest Deep cover: a steel chain hangs on a dark purple background with one red-hot cracked link, above the line Find the chain. Break it.

Every exploit arrives with the request that proves it and the file and line behind it, so teams fix the cause and break the chain in one change.

LONDON — 19 November 2026 — Autonomous pentest agents can now find real vulnerabilities at machine speed. Attackers will run them continuously. Security teams that still buy one pentest a year, and receive it as a PDF, are testing on a calendar while the other side tests on a loop. Phoenix Security today announced the general availability of Purple Pentest Deep, the agentic tier of Phoenix’s web and API pentest.

Purple Pentest Deep attacks a registered application from the outside, like an attacker. Then it does the defender’s half of the work in the same run. Every exploit carries the recorded exchange that proves it. Every finding gets a code verdict with a file and line. The report opens with the attack chains and a fix-first list, and each fix comes with a regression test and a command that reproduces the issue.

Purple Pentest Deep in 90 seconds: find the chain at runtime, trace it to the code, stop it at the pull request and inside the AI agent.

Where the cost lands

In December 2025 a team from Stanford, Carnegie Mellon and Gray Swan AI published “Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing” (arXiv 2512.09882). They put six existing AI agents and their own multi-agent system, ARTEMIS, against 10 professional penetration testers on a live university network of about 8,000 hosts.

ARTEMIS placed second overall and beat 9 of the 10 humans. It found 9 valid vulnerabilities with an 82% valid submission rate. Some ARTEMIS variants ran at about $18 an hour, against about $60 an hour for a professional tester. The same paper notes that the agents filed more false positives than the humans.

The cost of an outside-in test is falling toward the cost of a scan. The real cost now sits after the report lands.

A pentest finding names a URL, a parameter and a payload. A developer needs a file, a function and a change. Nothing in a traditional report connects the two. Someone reads the finding, guesses which handler serves that route, and writes a ticket. When the guess is wrong, the ticket bounces. When the guess is right but shallow, the team patches the symptom and leaves the cause.

Chains are where this hurts most. A debug endpoint leaks a secret, the secret forges a token, and the token reaches an admin action. Each step on its own looks medium. The chain is critical. A report that lists the three steps as three separate tickets hides the one fix that breaks the chain. An agent that files more findings, with a higher false positive rate, just delivers a larger backlog, faster.

What Purple Pentest Deep changes

The test starts from what the business depends on. Before any agent attacks, Purple Pentest Deep crawls the application inside the declared scope. It reads robots.txt, sitemap.xml, any OpenAPI description and the site map the team saved on the target. It also reads what the workspace already knows: the threat model, the business impact analysis and the workspace description. Secrets in that text are redacted before any agent sees them. A coordinating agent then splits pages, endpoints and attack classes across helper agents, which run in parallel inside an isolated sandbox. Every scan has a spending budget that a person sets, raises or stops.

An exploit counts only when it is proven. Each helper agent records the exchange that proves the exploit, and every report can turn it into a single curl command. When the scan ends on an application with a linked repository, Purple reads the code behind every finding. Each finding gets one of five verdicts: confirmed in code, seen at runtime only, plausible in code, refuted by code, or undetermined. The verdict cites the file and line. A finding the code disproves is flagged as refuted, so nobody spends a sprint on it. A finding confirmed at runtime and in code goes to the top of the queue. During the attack, the agents can also read the workspace’s code graph and look at the handler behind an endpoint before they aim the next request.

Findings end as changes a developer can merge. One click on Assess all builds the attack chains with a citation for every hop and ranks findings by business priority. Propose remediation turns each finding into the cited code, the fix, a regression test and the reproduction request. One change that breaks a chain is shown as one fix, not three tickets. Hunt, Phoenix’s code-side exploit hunter, works from the inside out and now shares one view with Purple Pentest Deep. Every Hunt finding that the live pentest also saw carries the label “Seen in Pentest scan”. Those are the ones to fix first.

Executive perspective

“An agent can break into an application in minutes now. Finding the hole was never the slow part. Purple Pentest Deep hands the developer the proof, the line of code and the fix, so a pentest ends as a merged change.”

— Francesco Cipollone, CEO and Co-Founder, Phoenix Security

How teams use it

We ran Purple Pentest Deep against our deliberately vulnerable benchmark application, so these numbers illustrate the workflow, not a benchmark. One Deep scan returned 81 findings. The triage agent ranked them by risk and reduced them to three attack paths:

  • Direct code execution on /api/calc, with no chain needed.
  • /api/system/info or /api/debug/env to internal key leakage, then command execution on localhost through /internal/run.
  • /api/debug/env to the JWT signing secret, to a forged admin token, to /api/admin/plugins/load.

Assess all cited src/server.js:69-82, src/jwt.js:6-20 and src/admin.js:35-40 for the hops of the last chain. Then it ranked a fix-first list and a phased rollout. Rotating the secret and removing the debug endpoint breaks the chain. Adding an auth check to the debug endpoint alone would not.

A team starting out picks one internet-facing application, registers it, proves ownership and gives it a site map and a workspace description. It runs one Deep scan with a modest budget and sorts the findings by code verdict. Then it runs a Hunt on the same repository with the scan attached, and hands the top fix to the owning team with the regression test and the reproduction command in the same ticket. Engineers still review and merge every fix.

At programme scale, this is the discipline Phoenix already applies to prioritisation. ClearBank, a Phoenix customer, reported a 98% reduction in container vulnerabilities, going from 467,000 to about 8,000 container findings through container lineage. Purple Pentest Deep applies the same rule to runtime findings. A finding earns a place in the queue only when it carries proof, a code location and an owner.

Availability

Purple Pentest Deep is generally available today. Teams register an application, prove ownership and set a budget for each scan. Documentation and demos are at phoenix.security.

About Phoenix Security

Phoenix Security is an Actionable ASPM platform that correlates vulnerabilities from code to cloud, turning fragmented findings into a single, prioritized remediation flow. Through reachability analysis, contextual deduplication and risk-based prioritization, Phoenix helps security and engineering teams cut the noise, fix what counts and scale without scaling headcount. Phoenix Purple brings graph-native scanning to AI-generated code. Phoenix AI is assistive and human-aligned: teams review, approve and merge.

International Sales Engineer — founding SE globally at Phoenix Security.

Discuss this blog with our community on Slack

Join our AppSec Phoenix community on Slack to discuss this blog and other news with our professional security team

From our Blog

On 16 November, Optimizely snippets on 178 brands’ websites served a crypto clipper, card skimmer and iOS exploit loader for about 19 hours. No customer backend was breached and no CVE exists. The trusted script did the work. Here’s the attack chain, IOCs, detection steps and the CSP settings that actually stopped it.
Sarah Mitchell
Phoenix Security has joined Anthropic’s Cyber Verification Program and is now an integration partner of OpenAI’s Daybreak Defense Factory. Frontier models made finding vulnerabilities cheap, and fixing is still slow. Phoenix findings arrive in the fix loop deduplicated, reachability-checked, owned and tied to a file and line, so engineers review real fixes.
Ksenia Mityushkina
Java4Shell (CVE-2026-114938) is a heap overflow in OpenJDK’s AVX-512 Base64 decoder, affecting Java 17.0.6 through 27. Calif claims pre-auth RCE in default Keycloak, Jira, Confluence, Jenkins, Artifactory and PingFederate, plus a heap leak. Hardware decides exposure: only x86 servers with AVX-512 VBMI run the vulnerable code.
Marcus Webb
Derek

Derek Fisher

Head of product security at a global fintech

Derek Fisher – Head of product security at a global fintech. Speaker, instructor, and author in application security.

Derek is an award winning author of a children’s book series in cybersecurity as well as the author of “The Application Security Handbook.” He is a university instructor at Temple University where he teaches software development security to undergraduate and graduate students. He is a speaker on topics in the cybersecurity space and has led teams, large and small, at organizations in the healthcare and financial industries. He has built and matured information security teams as well as implemented organizational information security strategies to reduce the organizations risk.

Derek got his start in the hardware engineering space where he learned about designing circuits and building assemblies for commercial and military applications. He later pursued a computer science degree in order to advance a career in software development. This is where Derek was introduced to cybersecurity and soon caught the bug. He found a mentor to help him grow in cybersecurity and then pursued a graduate degree in the subject.

Since then Derek has worked in the product security space as an architect and leader. He has led teams to deliver more secure software in organizations from multiple industries. His focus has been to raise the security awareness of the engineering organization while maintaining a practice of secure code development, delivery, and operations.

In his role, Jeevan handles a range of tasks, from architecting security solutions to collaborating with Engineering Leadership to address security vulnerabilities at scale and embed security into the fabric of the organization.

Jeevan Singh

Jeevan Singh

Founder of Manicode Security

Jeevan Singh is the Director of Security Engineering at Rippling, with a background spanning various Engineering and Security leadership roles over the course of his career. He’s dedicated to the integration of security practices into software development, working to create a security-aware culture within organizations and imparting security best practices to the team.
In his role, Jeevan handles a range of tasks, from architecting security solutions to collaborating with Engineering Leadership to address security vulnerabilities at scale and embed security into the fabric of the organization.

James

James Berthoty

Founder of Latio Tech

James Berthoty has over ten years of experience across product and security domains. He founded Latio Tech to help companies find the right security tools for their needs without vendor bias.

christophe

Christophe Parisel

Senior Cloud Security Architect

Senior Cloud Security Architect

Chris

Chris Romeo

Co-Founder
Security Journey

Chris Romeo is a leading voice and thinker in application security, threat modeling, and security champions and the CEO of Devici and General Partner at Kerr Ventures. Chris hosts the award-winning “Application Security Podcast,” “The Security Table,” and “The Threat Modeling Podcast” and is a highly rated industry speaker and trainer, featured at the RSA Conference, the AppSec Village @ DefCon, OWASP Global AppSec, ISC2 Security Congress, InfoSec World and All Day DevOps. Chris founded Security Journey, a security education company, leading to an exit in 2022. Chris was the Chief Security Advocate at Cisco, spreading security knowledge through education and champion programs. Chris has twenty-six years of security experience, holding positions across the gamut, including application security, security engineering, incident response, and various Executive roles. Chris holds the CISSP and CSSLP certifications.

jim

Jim Manico

Founder of Manicode Security

Jim Manico is the founder of Manicode Security, where he trains software developers on secure coding and security engineering. Jim is also the founder of Brakeman Security, Inc. and an investor/advisor for Signal Sciences. He is the author of Iron-Clad Java: Building Secure Web Applications (McGraw-Hill), a frequent speaker on secure software practices, and a member of the JavaOne Rockstar speaker community. Jim is also a volunteer for and former board member of the OWASP foundation.

Join our Mailing list!

Get all the latest news, exclusive deals, and feature updates.

The IKIGAI concept
Protected By
Shield Security PRO