Skip to content
SPECIFICTION
Get listed

Rogue

github.com

Free plan Self-hosted
Visit github.com
Spec score 7.7 #14 of 27 in AI Red Teaming Tools

What it is

Rogue is a self-hosted platform for evaluating AI agents and conducting security red-team exercises. Automatic checks compare agent behavior with business policies and expected behavior, then produce pass/fail reports with reasoning. Its documented coverage spans more than 75 vulnerabilities, 12 security categories and 20 attack techniques, including encoding, social engineering and injection. Each vulnerability receives a CVSS-based score from 0 to 10. Rogue maps tests to frameworks such as OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, the EU AI Act, GDPR and OWASP API Top 10. It offers a server, terminal interface and non-interactive CLI for CI/CD. Supported protocols include A2A over HTTP, MCP over SSE or Streamable HTTP, and direct Python calls. OpenAI, Anthropic and Google models are available through LiteLLM. Reports export to Markdown, CSV or JSON, and seeded scans can be reproducible. The free plan costs nothing for personal and internal use; commercial hosting requires licensing.

Spec sheet

Purpose
Rogue is an AI agent evaluator and red team platform for stress-testing agents before attackers do.Read 1 Oct 2026 · github.com
Product
Rogue is an AI agent evaluation and red teaming platform for testing agent reliability and security.Read 30 Sep 2026 · github.com
Compliance
Rogue maps testing to eight compliance frameworks including OWASP, MITRE, NIST, GDPR and the EU AI Act.Read 1 Oct 2026 · github.com
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.Read 30 Sep 2026 · github.com
Maker
The license identifies Qualifire ltd as Rogue's licensor.Read 30 Sep 2026 · github.com
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.Read 30 Sep 2026 · github.com
Coverage
The repository states that Rogue covers 75+ vulnerabilities across 12 security categories and 20 attack techniques.Read 1 Oct 2026 · github.com
Evaluation
Automatic Evaluation tests agents against business policies and expected behaviors with pass/fail reports and reasoning.Read 1 Oct 2026 · github.com
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.Read 30 Sep 2026 · github.com
Interfaces
Rogue provides a server, terminal user interface and non-interactive CLI for CI/CD pipelines.Read 1 Oct 2026 · github.com
Model providers
Rogue lists OpenAI, Anthropic, and Google models via LiteLLM and requires an LLM API key to get started.Read 30 Sep 2026 · github.com
Models
Rogue supports OpenAI, Anthropic and Google models through LiteLLM.Read 1 Oct 2026 · github.com
Protocols
Supported agent protocols are A2A over HTTP, MCP over SSE or streamable HTTP, and direct Python function calls.Read 1 Oct 2026 · github.com
Red teaming
Red Teaming simulates adversarial attacks to find security vulnerabilities.Read 1 Oct 2026 · github.com
Reports
Rogue exports comprehensive reports in Markdown, CSV and JSON formats.Read 1 Oct 2026 · github.com
Reproducibility
Scans can use a random seed to make results reproducible.Read 30 Sep 2026 · github.com
Requirements
The quick start lists uvx, Python 3.10+, and an API key from OpenAI, Anthropic, or Google as prerequisites.Read 30 Sep 2026 · github.com
Risk scoring
Rogue assigns vulnerabilities a CVSS-based risk score from 0 to 10.Read 30 Sep 2026 · github.com
Runtime integrations
The AI AppSec product page lists LangChain, CrewAI, AutoGen, custom builds, SIEM systems and webhooks, including Splunk, Datadog and PagerDuty.Read 1 Oct 2026 · rogue.security
Scan limits
Basic scans use 5 curated vulnerabilities and 6 attacks, while full scans use 75+ vulnerabilities and 40+ attacks.Read 1 Oct 2026 · github.com
Security posture
Rogue Security states that its Trust Center provides information about SOC 2 compliance and data handling, and that it supports end-to-end encryption and zero-data-egress in-VPC deployment.Read 1 Oct 2026 · rogue.security
Target users
The product is presented for security teams and developers building or deploying AI agents, including teams needing regression testing, security audits and compliance reporting.Read 1 Oct 2026 · github.com

Plans and prices

Personal and internal use Free Free for personal and internal use Read 1 Oct 2026 · github.com
Commercial hosting Priced on request Requires licensing · Contact [email protected] Read 1 Oct 2026 · github.com

Every Rogue plan and price →

Strong points and limits

Strong points

  • 75+ vulnerabilities across 12 security categories
  • CVSS-based risk scores from 0 to 10
  • CLI supports CI/CD pipelines
  • Reports export to Markdown, CSV and JSON
  • Custom tests and continuous monitoring supported

Limits

  • Requires an LLM API key to get started
  • Commercial hosting requires licensing
  • Basic scans cover only five vulnerabilities
  • Self-hosted deployment required

Who it suits

Rogue suits security teams and developers building or deploying AI agents who need automated evaluation, regression testing, security audits or compliance reporting. It supports A2A, MCP and Python agents in self-hosted deployments.

Verdict

Rogue combines automated policy evaluation with broad red-team coverage and compliance mappings. Its free personal and internal-use plan is available, while commercial hosting has separate licensing requirements.

Where Specifiction places it

Alternatives to RogueAll alternatives →