diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index 3c355f6..95e112e 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -1,4 +1,4 @@ -# Langalf Code of Conduct +# Agentic Security Code of Conduct In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to make participation in our project and our @@ -28,7 +28,7 @@ Examples of unacceptable behavior by participants include: - Conduct which could reasonably be considered inappropriate for the forum in which it occurs. -All Langalf forums and spaces are meant for professional interactions, and any behavior which could reasonably be considered inappropriate in a professional setting is unacceptable. +All Agentic Security forums and spaces are meant for professional interactions, and any behavior which could reasonably be considered inappropriate in a professional setting is unacceptable. ## Our Responsibilities @@ -38,9 +38,9 @@ Project maintainers have the right and responsibility to remove, edit, or reject ## Scope -This Code of Conduct applies to all content on Langalf website, Langalf’s GitHub organization, or any other official Langalf web presence allowing for community interactions, as well as at all official Langalf events, whether offline or online. +This Code of Conduct applies to all content on Agentic Security website, Agentic Security’s GitHub organization, or any other official Agentic Security web presence allowing for community interactions, as well as at all official Agentic Security events, whether offline or online. -The Code of Conduct also applies within project spaces and in public spaces whenever an individual is representing Langalf or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed or de facto representative at an online or offline event. +The Code of Conduct also applies within project spaces and in public spaces whenever an individual is representing Agentic Security or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed or de facto representative at an online or offline event. ## Conflict Resolution @@ -62,7 +62,7 @@ Please note that if you are experiencing or witnessing a discriminatory practice ## Reporting Violations -Violations of the Code of Conduct can be reported to Langalf via email to code_of_conduct@tangln.com. Project maintainers will determine whether the Code of Conduct was violated, and will issue an appropriate sanction, possibly including a written warning or expulsion from the project, project sponsored spaces, or project forums. We ask that you make a good-faith effort to resolve your conflict via the conflict resolution policy before submitting a report. +Violations of the Code of Conduct can be reported to Agentic Security via email to code_of_conduct@tangln.com. Project maintainers will determine whether the Code of Conduct was violated, and will issue an appropriate sanction, possibly including a written warning or expulsion from the project, project sponsored spaces, or project forums. We ask that you make a good-faith effort to resolve your conflict via the conflict resolution policy before submitting a report. Violations of the Code of Conduct can occur in any setting, even those unrelated to the project. We will only consider complaints about conduct that has occurred within one year of the report. diff --git a/FEATURES-for-organizations.md b/FEATURES-for-organizations.md index 34ee049..81a2c0f 100644 --- a/FEATURES-for-organizations.md +++ b/FEATURES-for-organizations.md @@ -1,6 +1,6 @@ -# Langalf - Features for Organizations +# Agentic Security - Features for Organizations -This feature list outlines the advanced capabilities of Langalf to assist in integrating high-security, low-latency language model applications into organizational infrastructure, with a particular focus on detecting and preventing prompt injection and jailbreak attempts. +This feature list outlines the advanced capabilities of Agentic Security to assist in integrating high-security, low-latency language model applications into organizational infrastructure, with a particular focus on detecting and preventing prompt injection and jailbreak attempts. ## 1. Exclusive Pentest with a 40k Jailbreak Dataset @@ -16,6 +16,6 @@ Implements feedback loops and LLMOps for continuous monitoring and improvement, ## 4. Reduced dependencies -Self-Contained Runtime Environment: Langalf operates within a self-contained runtime. This significantly lowers the barrier to entry for organizations by minimizing the complexity typically associated with setting up and maintaining LLM applications and infra. +Self-Contained Runtime Environment: Agentic Security operates within a self-contained runtime. This significantly lowers the barrier to entry for organizations by minimizing the complexity typically associated with setting up and maintaining LLM applications and infra. This library approach not only simplifies the architecture but also reduces potential points of failure and latency issues associated with external dependencies diff --git a/Readme.md b/Readme.md index e1da58d..e0ea01a 100644 --- a/Readme.md +++ b/Readme.md @@ -10,13 +10,13 @@

-GitHub Contributors -GitHub Last Commit - -Downloads -GitHub Issues -GitHub Pull Requests -Github License +GitHub Contributors +GitHub Last Commit + +Downloads +GitHub Issues +GitHub Pull Requests +Github License

@@ -40,23 +40,23 @@ - Comprehensive Reporting Tools 📊: Offers detailed reports of vulnerability, helping teams to quickly understand and respond to security incidents. - Customizable Rule Sets 🛠️: Allows users to define custom attack rules and parameters to meet specific prompt attacks needs and compliance standards. -Note: Please be aware that Langalf is designed as a safety scanner tool and not a foolproof solution. It cannot guarantee complete protection against all possible threats. +Note: Please be aware that Agentic Security is designed as a safety scanner tool and not a foolproof solution. It cannot guarantee complete protection against all possible threats. ## 📦 Installation -To get started with Langalf, simply install the package using pip: +To get started with Agentic Security, simply install the package using pip: ```shell -pip install langalf +pip install agentic_security ``` ## ⛓️ Quick Start ```shell -langalf +agentic_security -2024-04-13 13:21:31.157 | INFO | langalf.probe_data.data:load_local_csv:273 - Found 1 CSV files -2024-04-13 13:21:31.157 | INFO | langalf.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv'] +2024-04-13 13:21:31.157 | INFO | agentic_security.probe_data.data:load_local_csv:273 - Found 1 CSV files +2024-04-13 13:21:31.157 | INFO | agentic_security.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv'] INFO: Started server process [18524] INFO: Waiting for application startup. INFO: Application startup complete. @@ -64,18 +64,18 @@ INFO: Uvicorn running on http://0.0.0.0:8718 (Press CTRL+C to quit) ``` ```shell -python -m langalf +python -m agentic_security # or -langalf --help +agentic_security --help -langalf --port=PORT --host=HOST +agentic_security --port=PORT --host=HOST ``` ## LLM kwargs -Langalf uses plain text HTTP spec like: +Agentic Security uses plain text HTTP spec like: ```http POST https://api.openai.com/v1/chat/completions @@ -102,16 +102,16 @@ TBD ## Adding own dataset -To add your own dataset you can place one or multiples csv files with `prompt` column, this data will be loaded on `langalf` startup +To add your own dataset you can place one or multiples csv files with `prompt` column, this data will be loaded on `agentic_security` startup ``` -2024-04-13 13:21:31.157 | INFO | langalf.probe_data.data:load_local_csv:273 - Found 1 CSV files -2024-04-13 13:21:31.157 | INFO | langalf.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv'] +2024-04-13 13:21:31.157 | INFO | agentic_security.probe_data.data:load_local_csv:273 - Found 1 CSV files +2024-04-13 13:21:31.157 | INFO | agentic_security.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv'] ``` ## Extending dataset collections -1. Add new metadata to langalf.probe_data.REGISTRY +1. Add new metadata to agentic_security.probe_data.REGISTRY ```python { @@ -194,7 +194,7 @@ class Stenography: In the example of custom integration, we use `/v1/self-probe` for the sake of integration testing. ```python -POST https://langalf-preview.vercel.app/v1/self-probe +POST https://agentic_security-preview.vercel.app/v1/self-probe Authorization: Bearer XXXXX Content-Type: application/json @@ -236,7 +236,7 @@ TBD ## Documentation -For more detailed information on how to use Langalf, including advanced features and customization options, please refer to the official documentation. +For more detailed information on how to use Agentic Security, including advanced features and customization options, please refer to the official documentation. ## Roadmap and Future Goals @@ -249,19 +249,19 @@ Note: All dates are tentative and subject to change based on project progress an ## 👋 Contributing -Contributions to Langalf are welcome! If you'd like to contribute, please follow these steps: +Contributions to Agentic Security are welcome! If you'd like to contribute, please follow these steps: - Fork the repository on GitHub - Create a new branch for your changes - Commit your changes to the new branch - Push your changes to the forked repository -- Open a pull request to the main Langalf repository +- Open a pull request to the main Agentic Security repository Before contributing, please read the contributing guidelines. ## License -Langalf is released under the Apache License v2. +Agentic Security is released under the Apache License v2. ## Contact us @@ -269,7 +269,7 @@ Langalf is released under the Apache License v2. Book us with Cal.com -Book a 1-on-1 Session with the founders, to discuss any issues, provide feedback, or explore how we can improve langalf for you. +Book a 1-on-1 Session with the founders, to discuss any issues, provide feedback, or explore how we can improve agentic_security for you. ## Repo Activity diff --git a/langalf/__init__.py b/agentic_security/__init__.py similarity index 100% rename from langalf/__init__.py rename to agentic_security/__init__.py diff --git a/langalf/__main__.py b/agentic_security/__main__.py similarity index 91% rename from langalf/__main__.py rename to agentic_security/__main__.py index 3c25aac..441658a 100644 --- a/langalf/__main__.py +++ b/agentic_security/__main__.py @@ -4,7 +4,7 @@ import sys import fire import uvicorn -from langalf.app import app +from agentic_security.app import app class T: diff --git a/langalf/agent.py b/agentic_security/agent.py similarity index 100% rename from langalf/agent.py rename to agentic_security/agent.py diff --git a/langalf/app.py b/agentic_security/app.py similarity index 96% rename from langalf/app.py rename to agentic_security/app.py index 301a7cf..36bdea5 100644 --- a/langalf/app.py +++ b/agentic_security/app.py @@ -42,8 +42,8 @@ app.add_middleware( @app.get("/") async def root(): - langalf_path = Path(__file__).parent - return FileResponse(f"{langalf_path}/static/index.html") + agentic_security_path = Path(__file__).parent + return FileResponse(f"{agentic_security_path}/static/index.html") class LLMInfo(BaseModel): diff --git a/langalf/http_spec.py b/agentic_security/http_spec.py similarity index 100% rename from langalf/http_spec.py rename to agentic_security/http_spec.py diff --git a/langalf/probe_actor/__init__.py b/agentic_security/probe_actor/__init__.py similarity index 100% rename from langalf/probe_actor/__init__.py rename to agentic_security/probe_actor/__init__.py diff --git a/langalf/probe_actor/__main__.py b/agentic_security/probe_actor/__main__.py similarity index 100% rename from langalf/probe_actor/__main__.py rename to agentic_security/probe_actor/__main__.py diff --git a/langalf/probe_actor/fuzzer.py b/agentic_security/probe_actor/fuzzer.py similarity index 96% rename from langalf/probe_actor/fuzzer.py rename to agentic_security/probe_actor/fuzzer.py index 05c42f9..6bd8d89 100644 --- a/langalf/probe_actor/fuzzer.py +++ b/agentic_security/probe_actor/fuzzer.py @@ -4,8 +4,8 @@ import httpx from loguru import logger from pydantic import BaseModel -from langalf.probe_actor.refusal import refusal_heuristic -from langalf.probe_data.data import prepare_prompts +from agentic_security.probe_actor.refusal import refusal_heuristic +from agentic_security.probe_data.data import prepare_prompts IS_VERCEL = os.getenv("IS_VERCEL", "f") == "t" diff --git a/langalf/probe_actor/refusal.py b/agentic_security/probe_actor/refusal.py similarity index 100% rename from langalf/probe_actor/refusal.py rename to agentic_security/probe_actor/refusal.py diff --git a/langalf/probe_actor/test_refusal.py b/agentic_security/probe_actor/test_refusal.py similarity index 86% rename from langalf/probe_actor/test_refusal.py rename to agentic_security/probe_actor/test_refusal.py index 8a8349d..281a202 100644 --- a/langalf/probe_actor/test_refusal.py +++ b/agentic_security/probe_actor/test_refusal.py @@ -1,4 +1,4 @@ -from langalf.probe_actor.refusal import check_refusal +from agentic_security.probe_actor.refusal import check_refusal class TestCheckRefusal: diff --git a/langalf/probe_data/__init__.py b/agentic_security/probe_data/__init__.py similarity index 98% rename from langalf/probe_data/__init__.py rename to agentic_security/probe_data/__init__.py index b182c08..95023e6 100644 --- a/langalf/probe_data/__init__.py +++ b/agentic_security/probe_data/__init__.py @@ -82,7 +82,7 @@ REGISTRY = [ "url": "", }, { - "dataset_name": "Langalf", + "dataset_name": "Agentic Security", "num_prompts": 0, "tokens": 0, "approx_cost": 0.0, diff --git a/langalf/probe_data/data.py b/agentic_security/probe_data/data.py similarity index 98% rename from langalf/probe_data/data.py rename to agentic_security/probe_data/data.py index da28f88..e2541aa 100644 --- a/langalf/probe_data/data.py +++ b/agentic_security/probe_data/data.py @@ -6,8 +6,8 @@ from functools import lru_cache import pandas as pd from loguru import logger -from langalf.probe_data import stenography_fn -from langalf.probe_data.modules import adaptive_attacks +from agentic_security.probe_data import stenography_fn +from agentic_security.probe_data.modules import adaptive_attacks IS_VERCEL = os.getenv("IS_VERCEL", "f") == "t" diff --git a/langalf/probe_data/modules/__init__.py b/agentic_security/probe_data/modules/__init__.py similarity index 100% rename from langalf/probe_data/modules/__init__.py rename to agentic_security/probe_data/modules/__init__.py diff --git a/langalf/probe_data/modules/adaptive_attacks.py b/agentic_security/probe_data/modules/adaptive_attacks.py similarity index 100% rename from langalf/probe_data/modules/adaptive_attacks.py rename to agentic_security/probe_data/modules/adaptive_attacks.py diff --git a/langalf/probe_data/modules/test_adaptive_attacks.py b/agentic_security/probe_data/modules/test_adaptive_attacks.py similarity index 100% rename from langalf/probe_data/modules/test_adaptive_attacks.py rename to agentic_security/probe_data/modules/test_adaptive_attacks.py diff --git a/langalf/probe_data/stenography_fn.py b/agentic_security/probe_data/stenography_fn.py similarity index 100% rename from langalf/probe_data/stenography_fn.py rename to agentic_security/probe_data/stenography_fn.py diff --git a/langalf/probe_data/test_data.py b/agentic_security/probe_data/test_data.py similarity index 100% rename from langalf/probe_data/test_data.py rename to agentic_security/probe_data/test_data.py diff --git a/langalf/report_chart.py b/agentic_security/report_chart.py similarity index 100% rename from langalf/report_chart.py rename to agentic_security/report_chart.py diff --git a/langalf/static/index.html b/agentic_security/static/index.html similarity index 99% rename from langalf/static/index.html rename to agentic_security/static/index.html index ddb9aa8..a9e0bf2 100644 --- a/langalf/static/index.html +++ b/agentic_security/static/index.html @@ -47,8 +47,8 @@

🚀 - NEW: Star Langalf on Github 🚀

@@ -58,7 +58,7 @@
- @@ -67,7 +67,7 @@ d="..."> -