Feature/explore prompt injection tests

[chakravarthik27]

Description

This particular PR pertains to the implementation of prompt injection attack tests, which fall under the security category. It's worth noting that these tests carry immense significance when it comes to testing the safety and precautionary measures of LLM or text generation models such as Text-DaVinci-003 and hugging face models, among others. Their usefulness cannot be overstated.

---

➤ Fixes # (issue)

• Explore prompt injection tests

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Usage

Link to Notebook: Prompt_Injections_Tests.ipynb

from langtest import Harness
import os

# any llm API key 
os.environ["OPENAI_API_KEY"] = <YOUR_API_KEY>

# model security testing 
harness = Harness(
    task="security",
    model={
        'model': "text-davinci-003",
        "hub": "openai"
    },
    data={
        'data_source': 'Prompt-Injection-Attack'
    }
)


harness.generate().run().report()

Checklist:

• I've added Google style docstrings to my code.
• I've used pydantic for typing when/where necessary.
• I have linted my code
• I have added tests to cover my changes.

Screenshots (if appropriate):

[ArshaanNazir]

Looks fine. Kindly make sure that the prompts you have curated are working fine @chakravarthik27

[ArshaanNazir]

@chakravarthik27 kindly add usage guideline snippet as well in PR description