Skip to product experience

The agent harness for security research

Security research.
Under your command.

Enter the experience Explore the workspace
Decepticon ↖ Introduction
Continue

Interactive sample workspace. Scroll within the product or choose Guided tour.

↖ Back to the operationDecepticonOpen full sample

Published benchmark results.

Pass rate across 104 real-world exploitation challenges, as reported in the published comparison.

Decepticon
98.08%
Strix
96.15%
Shannonwhite-box
96.15%
PentestGPT
86.5%
Red-MIRROR
86%
XBOWcommercial
85%
Cyber-Auto
84.62%
MAPTA
76.9%
PentestAgent
50%
AutoPT
46%
VulnBot
6%

Decepticon: black-box, vulnerability tags as hint, 102 / 104 solved. Shannon shown white-box, hint-removed. Figures as published by each project.

Make it your operation

You have seen the operation. Now take command.

Your intent.
Your operation.

Explore the complete sample, or sign in to your workspace.

Log in to Decepticon Open the full sample No account needed · saved example operation
Questions before you begin?

Questions operators ask.

Is it safe to run against real targets?
Every action is bounded by scope and Rules of Engagement enforced at runtime. Out-of-scope actions are blocked before they fire, and OPSEC posture stays under operator control.
How is this different from a single AI agent?
Recon, initial access, and post-exploitation run as specialist sub-agents grounded in ATT&CK and Skillogy playbooks, not one generic prompt. You watch each one work in real time.
Do I stay in control of the run?
Yes. You set the OPPLAN up front through a guided interview. It tracks objectives, blockers, pivots, and evidence, and updates as the run evolves. You approve scope and every concession.
What proof is there that it works?
Highest published pass rate on the XBOW validation benchmark: 98.08% (102 of 104 challenges), ahead of every publicly reported agent.
How do I try it?
Explore the sample workspace on this page without signing in. It uses saved example data and does not run tests. Open the full sample workspace for the complete run and report. Live operations on authorized targets require a separate account and access.
What does it cost?
The read-only sample workspace is free. Solo and Pro rates are listed on the pricing page; access to live operations is handled separately.