
redamon v7.8.0
Autonomous AI red team framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then triages findings, implements code fixes, and opens pull requests.
Unmask the hidden before the world does
RedAmon is a next-generation, enterprise-grade platform for AI-driven penetration testing, at the forefront of agentic offensive security. It is self-hosted and supports multiple users and tenants, with role-based access control, Rules of Engagement enforcement and append-only audit trails. Security teams can run full-scope assessments on infrastructure they control: the attack surface mapped as a graph, exploitation driven by an agent behind human approval gates, and fixes delivered as pull requests. Local models are supported when data must not leave your environment.
LEGAL DISCLAIMER: This tool is intended for authorized security testing, educational purposes, and research only. Never use this system to scan, probe, or attack any system you do not own or have explicit written permission to test. Unauthorized access is illegal and punishable by law. By using this tool, you accept full responsibility for your actions. Read Full Disclaimer
🏆 Flagship result: RedAmon solves 101 / 104 (97.1%) of the XBOW web-security benchmark fully black-box. Every solve ships a complete, unedited raw agent session and a reproducible, step-by-step walkthrough: open any row and read exactly how the flag fell, tool call by tool call. Auditable, line by line. See the XBOW Validation Benchmark scorecard.
📊 Coverage, measured and self-scored: the Bug Bounty Coverage — The Full Taxonomy Audit (PDF, 124 pages) audits RedAmon against all 397 classes of web bug-bounty finding, one line at a time, naming the exact module, skill or scanner behind every verdict, and scoring the recon pipeline and the agentic system separately against their own remit. It is deliberately self-critical, it records what is missing as plainly as what is covered: 134 classes complete, 210 in the build backlog, 44 deliberately excluded, with one explicit decision for every class.