Heads up This site is currently under heavy development.
← all datasets
◆ Evals & benchmarks · Prompt injection & jailbreaks

Meta CyberSecEval

license: see source

Meta's LLM cybersecurity benchmarks (in Purple Llama) — insecure code generation, cyberattack helpfulness, code-interpreter abuse and prompt injection.

Summary

Purple Llama is an umbrella project that over time will bring together tools and evals to help the community build responsibly with open generative AI models. The initial release will include tools and evals for Cyber Security and Input/Output safeguards but we plan to contribute more in the near future.
from the project README
Formats
json
License
license: see source
Added
2026-09-10

Get it

From the project’s own instructions where it documents any; otherwise a plain clone.

  1. shell
    $ git clone https://github.com/meta-llama/PurpleLlama.git
  2. shell
    $ cd PurpleLlama && python3 -m venv ~/.venvs/CybersecurityBenchmarks && source ~/.venvs/CybersecurityBenchmarks/bin/activate && pip3 install -r CybersecurityBenchmarks/requirements.txt

    Python 3.10. Then `python3 -m CybersecurityBenchmarks.benchmark.run --help`.

Contents

894 files 42.8 MB repository

  • .json 341
  • .py 160
  • .yaml 105
  • .cpp 94
  • .md 79
  • (no ext) 24
  • .png 19
  • .js 16

Use it with

Commands are curated, not yet run by us.

jq — Stream the records one per line to see their shape.

sample.json
$ jq -c . sample.json

DuckDB — Query the file in place with SQL — DuckDB detects CSV, JSON and JSONL by extension.

sample.json
$ duckdb -c 'SELECT * FROM '\''sample.json'\'' LIMIT 10'
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →

    Send us feedback