Rakshak V2 Benchmark: What We Learned From Testing Our Autonomous Security System

Evaluating autonomous reasoning, security tool execution, evidence collection, and finding validation in real security workflows

Table of Contents

Testing Real Security Workflows

We’ve been building Rakshak V2 for quite some time, and during the development process, one fundamental question kept coming up:

How well does it actually perform when we put it through real security workflows?

Instead of just testing individual isolated features or simple synthetic prompts, we put Rakshak V2 through a structured benchmark to see how the complete system performs under realistic conditions.

The benchmark covered different stages of the autonomous security pipeline — from reconnaissance and security tool execution to analysis, evidence collection, finding validation, and automated report generation.

And honestly, the most useful part wasn’t just looking at the final scores. It was seeing where the system worked well, where it made mistakes, and which specific architectural components required further engineering effort.

What We Tested

The core objective was to test the platform as an integrated end-to-end unit, rather than treating an LLM or an individual security CLI tool as the product by itself. We evaluated how Rakshak handles:

Reconnaissance

Discovering target assets, domain structures, open ports, and surface attack vectors autonomously.

Security Tool Execution

Invoking scanners, parsers, and penetration testing tools with contextual parameter selection.

Target & Scope Handling

Enforcing out-of-scope boundaries and strict target constraints during automated tasks.

Vulnerability Analysis

Correlating multi-source findings to determine actual security exposure and risk severity.

Evidence Collection

Capturing non-repudiable logs, raw HTTP responses, network traces, and command outputs.

Finding Validation

Eliminating false positives by verifying potential flaws with deterministic validation checks.

Autonomous Reasoning

Evaluating model decision loops, adaptivity upon failure, and multi-step plan adjustments.

Report Generation

Compiling technical data, remediation guidelines, and executive summaries automatically.

Pipeline Stage Evaluation Focus Key Metric Target
Recon & Scope Asset identification accuracy & strict scope boundary enforcement Zero Out-of-Scope Execution
Tool Orchestration Correct CLI tool selection, dynamic flag tuning, & error recovery Tool Command Success Rate
Analysis & Validation False positive reduction through multi-stage deterministic checks Verifiable Finding Ratio
Evidence & Reporting Complete proof of concept log generation & structured executive summaries Audit-ready Technical Reports

What We Learned

Building an autonomous security system is significantly harder than simply connecting an AI model to security tools.

While modern foundation models excel at high-level reasoning and planning, the surrounding software architecture must guarantee that reasoning reliably translates into correct, deterministic, and verifiable actions.

Key Takeaway: AI reasoning is only as reliable as the verification mechanics wrapped around it. During the benchmark, we uncovered several edge cases where tool outputs were misparsed or initial plan hypotheses needed stricter validation guardrails. Those empirical findings directly fed back into our active engineering work across tool execution wrappers, payload validation, evidence capture, and report generation.

That’s exactly why we prioritized running a rigorous benchmark at this stage of development. We would rather identify edge cases and failure modes ourselves during internal stress testing than discover them later in production deployments.

This Is Still A Work In Progress

We don’t view this benchmark as a final static grade for Rakshak V2. For our engineering team, it represents a clear, objective snapshot of where the platform stands today and highlights the immediate path forward.

Rakshak V2 is under continuous development, and the empirical data gathered from this benchmark will directly shape upcoming platform iterations and agent control loops.

Explore The Complete Benchmark Data

We’ve published the full technical benchmark report separately, covering our evaluation methodology, testing criteria, and comprehensive performance metrics.

Read The Full Benchmark Report →

We will continue to share more of the underlying engineering, architectural patterns, and security research behind Rakshak as development progresses.

— Rudraksh AGI

Stay Updated with Rudraksh AI

Subscribe to our newsletter for the latest cybersecurity insights, tips, and exclusive tutorials delivered straight to your inbox.

Share
Home
About
Blog
Theme
Back