From 3b70098efe569f343e3930d6e59e1bfcac21cb12 Mon Sep 17 00:00:00 2001 From: cris Date: Thu, 4 Sep 2025 11:35:33 +0200 Subject: [PATCH] change nam of the project --- benchmarks/{prompt-bench => Prompt2PwnBench}/.env.example | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/README.md | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/main.py | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/metrics.ipynb | 0 .../metrics_experiment/.gitkeep | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/prompts.yml | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/requirements.txt | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/results/.gitkeep | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/server.py | 0 .../{prompt-bench => Prompt2PwnBench}/terminal_output/.gitkeep | 0 benchmarks/{prompt-bench => Prompt2PwnBench}/utils/helpers.py | 0 .../utils/portswigger_labs.json | 0 .../{prompt-bench => Prompt2PwnBench}/utils/portswiggerbot.py | 0 .../utils/topics_prefixes.json | 0 benchmarks/README.md | 2 +- 15 files changed, 1 insertion(+), 1 deletion(-) rename benchmarks/{prompt-bench => Prompt2PwnBench}/.env.example (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/README.md (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/main.py (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/metrics.ipynb (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/metrics_experiment/.gitkeep (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/prompts.yml (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/requirements.txt (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/results/.gitkeep (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/server.py (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/terminal_output/.gitkeep (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/utils/helpers.py (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/utils/portswigger_labs.json (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/utils/portswiggerbot.py (100%) rename benchmarks/{prompt-bench => Prompt2PwnBench}/utils/topics_prefixes.json (100%) diff --git a/benchmarks/prompt-bench/.env.example b/benchmarks/Prompt2PwnBench/.env.example similarity index 100% rename from benchmarks/prompt-bench/.env.example rename to benchmarks/Prompt2PwnBench/.env.example diff --git a/benchmarks/prompt-bench/README.md b/benchmarks/Prompt2PwnBench/README.md similarity index 100% rename from benchmarks/prompt-bench/README.md rename to benchmarks/Prompt2PwnBench/README.md diff --git a/benchmarks/prompt-bench/main.py b/benchmarks/Prompt2PwnBench/main.py similarity index 100% rename from benchmarks/prompt-bench/main.py rename to benchmarks/Prompt2PwnBench/main.py diff --git a/benchmarks/prompt-bench/metrics.ipynb b/benchmarks/Prompt2PwnBench/metrics.ipynb similarity index 100% rename from benchmarks/prompt-bench/metrics.ipynb rename to benchmarks/Prompt2PwnBench/metrics.ipynb diff --git a/benchmarks/prompt-bench/metrics_experiment/.gitkeep b/benchmarks/Prompt2PwnBench/metrics_experiment/.gitkeep similarity index 100% rename from benchmarks/prompt-bench/metrics_experiment/.gitkeep rename to benchmarks/Prompt2PwnBench/metrics_experiment/.gitkeep diff --git a/benchmarks/prompt-bench/prompts.yml b/benchmarks/Prompt2PwnBench/prompts.yml similarity index 100% rename from benchmarks/prompt-bench/prompts.yml rename to benchmarks/Prompt2PwnBench/prompts.yml diff --git a/benchmarks/prompt-bench/requirements.txt b/benchmarks/Prompt2PwnBench/requirements.txt similarity index 100% rename from benchmarks/prompt-bench/requirements.txt rename to benchmarks/Prompt2PwnBench/requirements.txt diff --git a/benchmarks/prompt-bench/results/.gitkeep b/benchmarks/Prompt2PwnBench/results/.gitkeep similarity index 100% rename from benchmarks/prompt-bench/results/.gitkeep rename to benchmarks/Prompt2PwnBench/results/.gitkeep diff --git a/benchmarks/prompt-bench/server.py b/benchmarks/Prompt2PwnBench/server.py similarity index 100% rename from benchmarks/prompt-bench/server.py rename to benchmarks/Prompt2PwnBench/server.py diff --git a/benchmarks/prompt-bench/terminal_output/.gitkeep b/benchmarks/Prompt2PwnBench/terminal_output/.gitkeep similarity index 100% rename from benchmarks/prompt-bench/terminal_output/.gitkeep rename to benchmarks/Prompt2PwnBench/terminal_output/.gitkeep diff --git a/benchmarks/prompt-bench/utils/helpers.py b/benchmarks/Prompt2PwnBench/utils/helpers.py similarity index 100% rename from benchmarks/prompt-bench/utils/helpers.py rename to benchmarks/Prompt2PwnBench/utils/helpers.py diff --git a/benchmarks/prompt-bench/utils/portswigger_labs.json b/benchmarks/Prompt2PwnBench/utils/portswigger_labs.json similarity index 100% rename from benchmarks/prompt-bench/utils/portswigger_labs.json rename to benchmarks/Prompt2PwnBench/utils/portswigger_labs.json diff --git a/benchmarks/prompt-bench/utils/portswiggerbot.py b/benchmarks/Prompt2PwnBench/utils/portswiggerbot.py similarity index 100% rename from benchmarks/prompt-bench/utils/portswiggerbot.py rename to benchmarks/Prompt2PwnBench/utils/portswiggerbot.py diff --git a/benchmarks/prompt-bench/utils/topics_prefixes.json b/benchmarks/Prompt2PwnBench/utils/topics_prefixes.json similarity index 100% rename from benchmarks/prompt-bench/utils/topics_prefixes.json rename to benchmarks/Prompt2PwnBench/utils/topics_prefixes.json diff --git a/benchmarks/README.md b/benchmarks/README.md index 17b35129..cc0cc14e 100644 --- a/benchmarks/README.md +++ b/benchmarks/README.md @@ -13,7 +13,7 @@ Currently, this are the benchmarks included: | [CTIBench](https://github.com/xashru/cti-bench) | Benchmark focused on evaluating LLM models' capabilities in understanding and processing Cyber Threat Intelligence (CTI) information. | | [PentestPerf](https://gitlab.com/aliasrobotics/alias_research/caiextensions/pentestperf) | An internal benchmarking framework that measures penetration testing capabilities of LLM models in a proprietary set of IT, OT and robotics scenarios. Reach out if you wish to cooperate in this direction. | | [CyberPII-Bench](https://github.com/aliasrobotics/cai/tree/main/benchmarks/cyberPII-bench/) | Benchmark designed to evaluate the ability of LLM models to maintain privacy and handle **Personally Identifiable Information (PII)** in cybersecurity contexts. Built from real-world data generated during offensive hands-on exercises conducted with **CAI (Cybersecurity AI)**. | -| [Prompt-Bench](https://github.com/aliasrobotics/cai/tree/main/benchmarks/prompt-bench/) | Benchmark designed to evaluate a fully automated integration of LLMs (Large Language Models) with no HITL (Human-in-the-Loop) into web application attack scenarios using **CAI (Cybersecurity AI)**. Its goal is to test various prompting strategies and different LLMs to assess their effectiveness in identifying vulnerabilities within web applications. | +| [Prompt2PwnBench](https://github.com/aliasrobotics/cai/tree/main/benchmarks/Prompt2PwnBench/) | Benchmark designed to evaluate a fully automated integration of LLMs (Large Language Models) with no HITL (Human-in-the-Loop) into web application attack scenarios using **CAI (Cybersecurity AI)**. Its goal is to test various prompting strategies and different LLMs to assess their effectiveness in identifying vulnerabilities within web applications. |