- Home
- AI Security Testing Tools
- PromptRAID
On the recordRead 10 Oct 202622 facts
PromptRAID
On the record
- ATLAS coverage
- Implemented mutation categories map to verified MITRE ATLAS technique IDs, while some listed categories remain unverified placeholders or have no generator yet.github.com · read 9 Oct 2026
- Installation
- The README recommends installing the CLI with pipx and also documents installation in a Python virtual environment.github.com · read 10 Oct 2026
- Intended users
- The project describes its intended use as systematic red-team testing and benchmarking of LLM-based agents across providers.github.com · read 10 Oct 2026
- Interface
- The project provides a command-line interface with commands for taxonomy, mutation, judging, running tests, demos, and reports.github.com · read 9 Oct 2026
- License
- PromptRAID is distributed under the MIT License, which permits use, copying, modification, distribution, sublicensing, and sale subject to its terms.github.com · read 10 Oct 2026
- Limitations
- The README says triggered prompt injection and data leakage appear in its taxonomy but do not yet have mutation generators.github.com · read 10 Oct 2026
- Maintainer
- The README identifies Shikhali Jamalzade (alisalive) as an independent offensive security researcher and the project author.github.com · read 10 Oct 2026
- Maker
- The repository names Shikhali Jamalzade (alisalive) as the author.github.com · read 9 Oct 2026
- Model providers
- The harness supports Anthropic, Gemini, Groq, Cerebras, and OpenRouter, including OpenAI-compatible endpoints.github.com · read 9 Oct 2026
- Payloads
- Its mutation engine generates prompt injection variants using encoding tricks, role-play framing, delimiter breaking, and indirect injection through tool or document output.github.com · read 10 Oct 2026
- Payload testing
- Its mutation engine generates prompt injection variants using encoding tricks, jailbreak framing, delimiter breaking, and indirect injection through tool or document output.github.com · read 9 Oct 2026
- Provider credentials
- Running tests requires at least one provider API key, with environment variables documented for Anthropic, Gemini, Groq, OpenRouter, and Cerebras.github.com · read 10 Oct 2026
- Providers
- The harness supports Anthropic, Gemini, Groq, Cerebras, and OpenRouter, including OpenAI-compatible endpoints.github.com · read 10 Oct 2026
- Purpose
- PromptRAID is an automated prompt injection red-teaming framework for LLM-based agents, mapped to MITRE ATLAS.github.com · read 10 Oct 2026
- Reports and storage
- PromptRAID exports JSON and HTML reports and stores runs and per-payload results in SQLite.github.com · read 10 Oct 2026
- Requirements
- The package requires Python 3.9 or later and asks users to configure at least one supported provider API key.github.com · read 9 Oct 2026
- Security classification
- The project maps prompt injection tests to MITRE ATLAS and describes them as red-team tests for LLM agents.github.com · read 10 Oct 2026
- Taxonomy
- Mutation categories map to MITRE ATLAS technique IDs, which the project says it checks against the live ATLAS matrix.github.com · read 10 Oct 2026
