MEMORY
Grow the knowledge
Conditions, findings and reasons for failure accumulate in the RAG database. Last time’s lessons shape the next test plan.
↗AUTONOMOUS PENETRATION RESEARCH
AI Self-Growing Penetration System
It gathers, it tests, it learns from the results.
Each finding becomes knowledge for the next test.
A local GLM, labeled labs and a growing RAG database.
LMR is building a foundation where penetration testing keeps improving.
In-specification tallies from our labs and in-house environments. Not a third-party evaluation, and not a performance guarantee for customer environments.
Rather than only running fixed scenarios, the GLM chooses the next test from what it observes. Results are scored and fed back into the next decision.
“Self-growth” here does not mean updating model weights. It is a mechanism that updates the knowledge, tools and prompts in continuous use, from test results.
MEMORY
Conditions, findings and reasons for failure accumulate in the RAG database. Last time’s lessons shape the next test plan.
↗TOOL
New detection patterns go into the matchers. Checking against known answers widens what can be verified.
↗PROMPT
Scoring feedback feeds the standing instructions, guiding decisions to adopt, retry or stop.
↗An update does not guarantee improvement every time. Evaluation and demotion separate real gains from mistakes.
Information is collected from seven sources every ten minutes. A daily test cycle tries the knowledge, evaluates it and makes it usable.
Select a step to see the role of each stage.
COLLECT / 10 MINUTES
Public reports and papers, product vulnerability advisories, reproduction tests, expert knowledge, AI attack intelligence, autonomous discovery and our own observations — seven sources, collected continuously.
Techniques and their test status saved to the collection DB
Test results flow into the next cycle ↗What the AI finds is not taken as truth as-is. Roles and scoring criteria are kept separate to confirm the result.
EXPLORE
From past knowledge and observations, the GLM selects the next test. It uses seven tools and records what it finds.
Observe → Reason → ActREVIEW
Candidate techniques are reviewed for quality. R2 decides to adopt, retry or stop, carrying the cycle on.
Candidate → Review → DecideSCORE
A resident process detects completed experiments, compares against 36 matchers and the labs’ ground truth, and records false positives and misses too.
Result → Compare to truth → EvaluateThe same technique is compared across a vulnerable and a fixed environment. We evaluate both finding what is there and not flagging what is not.
Detecting an issue that is in the ground truth is a true positive. Issues it misses are recorded too, for improvement.
Techniques that still fire on a fixed target are caught. Knowledge that causes false positives is demoted and excluded from real-world use.
Web apps, REST APIs, authentication and authorization, file handling, mail servers and more.
Docker and VM labs are used as needed, testing where the answer is known.
TP ÷ (TP + FP)
4,175 ÷ 4,194 ≒ 99.5%
6,452 scored in total, 11 fewer than the number of experiments. The 99.5% is the precision of what was detected, not the share of all issues found. For reference, TP ÷ (TP + miss) is about 81.2%. All are values calculated from the specification’s lab tallies.
More knowledge is not automatically good growth. Reverse-testing on fixed environments, and a gate before anything enters the knowledge pool, hold back the return of errors.
Existing reproduced techniques are re-tested on fixed environments. Any false positive is demoted and dropped from the candidates for real-world use.
RECHECK / DEMOTERe-registering knowledge from past successes is checked as well. Problematic records are excluded and the knowledge is rebuilt from the sound ones.
CHECK BEFORE PROMOTIONE1–E4 are this system’s own status categories. E4 is the definition of the final stage; it does not indicate a track record of customer engagements.
The GLM’s judgment, the labs’ observations and the RAG’s memory in one cycle. Each stage is linked by records and state.
Public sources / autonomous discovery / own observation
PostgreSQL
API / streaming
An inference base on four GPUs
Oversees lab testing, evaluation and knowledge updates
Verified techniques and past know-how,
managed by state for search and reuse
weak / fixed · Docker / VM
Scope check / run log / report
A logical diagram based on specification v1.0. It does not represent wiring or the physical placement of machines. Current real-world testing is limited to two LMR-managed domains.
Live progress and commentary, the findings and a PDF report, all connected. The course of the assessment becomes material for planning your response.
The panel at right illustrates the kind of output. It is not an actual customer report.
Scope, conditions and findings
Scope limited / destructive actions refused / DoS refused / abnormally long runs watched
Designed for testing our own systems, or environments whose authorization and scope have been confirmed.In this system, the RAG-DB knowledge, tools such as the matchers, and the prompts in continuous use are updated from scoring results. It does not mean retraining the model’s own weights.
In the specification, collection, testing, scoring and knowledge updates run as an automatic cycle, while people watch and handle anomalies. Setting the scope at adoption, confirming authorization, key decisions and operational management are still needed.
It is the detection precision computed from the 4,175 true positives and 19 false positives in the specification. It is not a detection rate, which would include the 965 misses. It is a tally under lab conditions and does not guarantee the same figure in a customer environment.
We review the target systems, test scope, labs needed, compute and reporting/operations to design a configuration. Under the current specification, real-world testing is limited to LMR-managed domains; extending to other environments requires individual design and confirmation.
The figures on this page are tallies recorded in “AI Self-Growing Penetration System, Detailed Specification v1.0”, reviewed on 17 November 2026. The cycle display is a demo explaining the mechanism, not a live console of the running system.
Tell us the system you want tested and the challenges you face.
Together we will consider how to connect LMR’s research base to your environment.
What to include: target system / what you want tested / number of users / existing equipment / desired operation