Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

RedForge review

Free#6 of 29 in AI Security Testing Tools

A self-hosted toolkit for testing LLM security risks and producing compliance-ready reports.

8.6/10Editor score
Visit RedForge
RedForge8.6 Visit RedForge

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

RedForge is an open-source security testing platform for large language model applications. It is designed for security engineers who need to scan authorized models and endpoints for prompt injection, jailbreaks, insecure output handling, data exposure, excessive agency, hallucination, and other OWASP LLM Top 10 risks. Its self-hosted deployment model suits teams that want control over testing infrastructure and report handling.

Coverage is the central strength. RedForge provides 49+ security probes, a 37-strategy payload mutation engine, and bidirectional scanning of model inputs and outputs. Detection options include YARA-style, similarity, regex, keyword, code, and unsafe-content detectors. Teams can extend the platform with custom YAML probes and Python plugins, while multiple provider adapters support OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Mistral, Ollama, HuggingFace Hub, and generic REST endpoints. Local-model support adds another path for testing deployments outside hosted APIs.

The reporting and automation layer makes RedForge particularly relevant to governance-focused programs. It offers REST API and Python SDK access, CI integration, and outputs in HTML, Markdown, SARIF, JSON, and audit report formats. Reports can map findings to the NIST AI RMF, EU AI Act, ISO/IEC 42001, GDPR, and OWASP. Choose RedForge when extensible testing, provider coverage, and compliance-oriented reporting matter more than a managed service. Teams seeking a hosted product or a narrowly focused scanner may prefer a different deployment model.

RedForge pros and cons

  • Where it wins
    • 49+ OWASP LLM Top 10 probes with prompt-injection and jailbreak testing
    • 37-strategy mutation engine plus bidirectional input and output scanning
    • SARIF, JSON, and framework-mapped reports for audit workflows
  • Where it doesn't
    • Self-hosted deployment places setup and maintenance responsibility on the team
    • The broad feature set may exceed the needs of teams seeking a narrow scanner
    • Extending coverage requires custom YAML probes or Python plugin work

RedForge fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update