RedForge
RedForge is a free, open-source platform for red teaming and vulnerability scanning of large language models.
What RedForge is
RedForge is a free, open-source platform for red teaming and vulnerability scanning of large language models. It lists 49+ probes, full OWASP LLM Top 10 coverage, and YAML probes that can be added without Python. Attack modules include PAIR, Crescendo multi-turn escalation, Skeleton Key, many-shot jailbreaking, and GCG adversarial suffixes. Its mutation engine expands two payloads into 37 variants using encoding, Unicode, cognitive reframing, and structural injection.
Provider adapters cover OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Mistral, Ollama, HuggingFace, and generic REST endpoints. Ollama can run locally without an API key. Scans automatically produce JSON, JSONL audit, and failures reports, with HTML, Markdown, SARIF, JSON, audit, and failures formats also listed. Compliance reports cover NIST AI RMF, EU AI Act, ISO/IEC 42001, GDPR, and OWASP LLM Top 10, with custom YAML frameworks supported. RedForge can emit SARIF for GitHub Code Scanning and exit with status 1 on critical or high findings for CI use. It is self-hosted for Linux and API use, licensed under Apache 2.0, and intended for authorized use only; probe payloads are listed under CC0. The CLI requires an authorization value indicating owned, authorized, or research use.
Good
- Lists 49+ probes and full OWASP LLM Top 10 coverage.
- YAML probes can be added without Python.
- Supports many model-provider adapters, including local Ollama.
- Exports SARIF for GitHub Code Scanning and CI gating.
- Offers multiple report formats and compliance frameworks.
Watch out
- CLI requires an authorization value for use.
- Docker deployment runs with a read-only filesystem.
- REST API limits clients to 10 scan requests per minute.
Who it suits
RedForge suits teams that need self-hosted LLM security testing with configurable probes, compliance reports, or CI integration. It is for authorized use, and its CLI requires an authorization value.
Verdict
RedForge combines probe-based testing, reporting, and CI integration in a self-hosted tool. Its authorization requirement and documented security controls are important considerations for deployment.
Plans and prices
From RedForge's own pricing page, checked 9 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| RedForge | Free | Apache 2.0 open-source software · install with pip |
The facts
Each one read from RedForge's own pages, with the date it was checked.
What it does
- Attack methods
- Attack modules include PAIR, Crescendo multi-turn escalation, Skeleton Key, many-shot jailbreaking, and GCG adversarial suffixes.checked 9 Oct 2026
- Attack modules
- Its attack modules include PAIR, Crescendo multi-turn escalation, Skeleton Key, many-shot jailbreaking, and GCG adversarial suffixes.checked 9 Oct 2026
- CI integration
- RedForge can emit SARIF for GitHub Code Scanning and exits with status 1 on critical or high findings for use as a CI gate.checked 9 Oct 2026
- Compliance
- Compliance reporting covers NIST AI RMF, EU AI Act, ISO/IEC 42001, GDPR, and OWASP LLM Top 10, and users can add custom YAML frameworks.checked 9 Oct 2026
- Deployment
- The Docker instructions say the container runs as non-root user redforge (UID 1001) with a read-only filesystem.checked 9 Oct 2026
- Detectors
- The README lists seven detector types, including YARA-style, similarity, refusal, regex, keyword, code, and unsafe-content detectors.checked 9 Oct 2026
- Guardrails
- A bidirectional guardrail pipeline scans inputs and outputs for prompt injection, PII, toxicity, and secrets.checked 9 Oct 2026
- Integrations
- It can export SARIF for GitHub Code Scanning and documents a GitHub Actions workflow that uploads the SARIF file.checked 9 Oct 2026
- License
- The project is released under the Apache 2.0 license, and the README says probe payloads are released under CC0.checked 9 Oct 2026
- License and use
- The repository identifies the license as Apache 2.0 and says the tool is for authorized use only.checked 9 Oct 2026
- Local use
- The Ollama adapter runs locally without an API key, and the README describes it as zero cost.checked 9 Oct 2026
- Model providers
- It lists adapters for OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Mistral, Ollama, HuggingFace, and generic REST endpoints.checked 9 Oct 2026
- Mutation engine
- The mutation engine expands two payloads to 37 variants across encoding, Unicode, cognitive reframing, and structural injection strategies.checked 9 Oct 2026
- Probe coverage
- It lists 49+ probes and full OWASP LLM Top 10 coverage, with YAML probes that can be added without Python.checked 9 Oct 2026
- Providers
- The README lists provider adapters for OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Mistral, Ollama, HuggingFace, and generic REST endpoints.checked 9 Oct 2026
- Purpose
- RedForge is an LLM security testing platform for red teaming and vulnerability scanning.checked 9 Oct 2026
- Reports
- Scans automatically produce JSON, JSONL audit, and failures reports, with additional HTML, Markdown, SARIF, JSON, audit, and failures formats.checked 9 Oct 2026
- Security controls
- Documented controls include masking API keys in logs, setting result files to mode 0600, bearer-token REST API authentication, disabled-by-default CORS, and a rate limit of 10 scan requests per minute per client.checked 9 Oct 2026
- Usage requirement
- The CLI requires an authorization value indicating owned, authorized, or research use.checked 9 Oct 2026
Alternatives to RedForge
- 1
OpenSecureAI Scanner
Free planOpen sourceWebAPILinuxmacOS8.1From $49 a month - 2
PromptGuard
Free planWebAPIExtensionLinux7.9From $19 a month - 3
Promptfoo
Free planOpen sourceWebAPILinuxmacOS7.8Free plan - 4
Giskard
Free planOpen sourceWebAPILinuxSelf-hosted7.6Free plan - 5
AIRTA Red Team
Free planOpen sourceWebAPILinuxmacOS7.5Free plan - 6
CyberSecEval
Free planOpen sourceWebAPILinuxmacOS7.5Free plan