Rogue

7.1easy start · #7 of 27
in AI Red Teaming Tools

Free to practise onyes
Free trialnot on record
Well documentedyes
Runs where you worknot on record

Runs on self-hosted.

Visit site Alternatives

Rogue is ranked #7 of 27 in AI red teaming tools on The Geeks Club. It runs on Self-hosted. There is a free plan.

Rogue plans and pricing

All plans

Personal and internal use Free Free for personal and internal use github.com · 1 Oct 2026

Commercial hosting Not published Requires licensing · Contact [email protected] github.com · 1 Oct 2026

Compared on AI red teaming tools

Free plan: Yes
Attack categories: Encoding; Social Engineering; Injection; Semantic; Technical
Target systems: A2A agents; MCP agents; Python agents
Automation level: automated
Custom tests: Yes
Deployment: self_hosted
Continuous monitoring: Yes
Report exports: Markdown; CSV; JSON

Best Rogue alternatives

See all 20

AgentSeal 0 of 4 in the starter kit Lesson 17.3 F5 BIG-IP APM 0 of 4 in the starter kit Lesson 27.3 OpenSecureAI Scanner 0 of 4 in the starter kit Lesson 37.2 Promptfoo 0 of 4 in the starter kit Lesson 47.2 NVADER 0 of 4 in the starter kit Lesson 57.1 RedAmon 0 of 4 in the starter kit Lesson 67.1

The record

Product: Rogue is an AI agent evaluation and red teaming platform for testing agent reliability and security.
Evaluation: Automatic evaluation checks agents against business policies and expected behavior and produces pass/fail reports with reasoning.
Red teaming: The repository describes 75+ vulnerabilities across 12 security categories, with attack techniques including encoding, social engineering, and injection.
Risk scoring: Rogue assigns vulnerabilities a CVSS-based risk score from 0 to 10.
Frameworks: The documented framework coverage includes OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, EU AI Act, GDPR, and OWASP API Top 10.
Interfaces: Rogue provides a server, a terminal interface, and a non-interactive CLI for CI/CD pipelines.
Protocols: The repository lists A2A over HTTP, MCP over SSE or Streamable HTTP, and direct Python function calls as supported agent protocols.
Model providers: Rogue lists OpenAI, Anthropic, and Google models via LiteLLM and requires an LLM API key to get started.
Reports: Rogue can export reports in Markdown, CSV, and JSON formats.
Reproducibility: Scans can use a random seed to make results reproducible.
Requirements: The quick start lists uvx, Python 3.10+, and an API key from OpenAI, Anthropic, or Google as prerequisites.
License: The repository license is the Qualifire OSS License, combining MIT terms with a Commons Clause that excludes selling the software or offering it as a paid hosted service.
Commercial use: The README says Rogue is free for personal and internal use and that commercial hosting requires licensing; it provides [email protected] for contact.
Maker: The license identifies Qualifire ltd as Rogue's licensor.
Price from: Free

Where it ranks on The Geeks Club

Best AI Red Teaming Tools in 2026#7 of 27

Is Rogue yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote Rogue

Sources

github.com/rogue-security/rogue· checked 30 Sept 2026
github.com/rogue-security/rogue/blob/main/LICENSE.· checked 30 Sept 2026
rogue.security/security· checked 1 Oct 2026
rogue.security/platform/ai-appsec· checked 1 Oct 2026