Skip to content

DeepTeam is a framework to red team LLMs and AI agents.

docs for vulnerabilities updated

A-Vamshide9786e6ecee
diff --git a/docs/docs/red-teaming-agentic-vulnerabilities-goal-theft.mdx b/docs/docs/red-teaming-agentic-vulnerabilities-goal-theft.mdx
index 1e7325e6..6b3ff942 100644
--- a/docs/docs/red-teaming-agentic-vulnerabilities-goal-theft.mdx
+++ b/docs/docs/red-teaming-agentic-vulnerabilities-goal-theft.mdx
@@ -11,12 +11,11 @@ The goal theft vulnerability evaluates whether an AI agent can **protect its int
```python
from deepteam.vulnerabilities.agentic import GoalTheft
-goal_theft = GoalTheft(purpose="General assistant")
+goal_theft = GoalTheft()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `GoalTheft` vulnerability:
+There are **FIVE** optional parameters when creating a `GoalTheft` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-agentic-vulnerabilities-recursive-hijacking.mdx b/docs/docs/red-teaming-agentic-vulnerabilities-recursive-hijacking.mdx
index 0428d9e1..8a4155f7 100644
--- a/docs/docs/red-teaming-agentic-vulnerabilities-recursive-hijacking.mdx
+++ b/docs/docs/red-teaming-agentic-vulnerabilities-recursive-hijacking.mdx
@@ -11,12 +11,11 @@ The recursive hijacking vulnerability evaluates whether an AI agent can **resist
```python
from deepteam.vulnerabilities.agentic import RecursiveHijacking
-recursive_hijacking = RecursiveHijacking(purpose="General assistant")
+recursive_hijacking = RecursiveHijacking()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `RecursiveHijacking` vulnerability:
+There are **FIVE** optional parameters when creating a `RecursiveHijacking` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-bfla.mdx b/docs/docs/red-teaming-vulnerabilities-bfla.mdx
index 21b977fa..08edf020 100644
--- a/docs/docs/red-teaming-vulnerabilities-bfla.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-bfla.mdx
@@ -11,12 +11,11 @@ The BFLA (Broken Function Level Authorization) vulnerability evaluates whether a
```python
from deepteam.vulnerabilities import BFLA
-bfla = BFLA(purpose="General assistant")
+bfla = BFLA()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `BFLA` vulnerability:
+There are **FIVE** optional parameters when creating a `BFLA` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-bias.mdx b/docs/docs/red-teaming-vulnerabilities-bias.mdx
index b537058e..a77bc692 100644
--- a/docs/docs/red-teaming-vulnerabilities-bias.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-bias.mdx
@@ -11,12 +11,11 @@ The bias vulnerability is designed to test whether an LLM can **identify, mitiga
```python
from deepteam.vulnerabilities import Bias
-bias = Bias(purpose="General assistant")
+bias = Bias()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `Bias` vulnerability:
+There are **FIVE** optional parameters when creating a `Bias` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-bola.mdx b/docs/docs/red-teaming-vulnerabilities-bola.mdx
index 51d7389c..bbccf695 100644
--- a/docs/docs/red-teaming-vulnerabilities-bola.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-bola.mdx
@@ -11,12 +11,11 @@ The BOLA (Broken Object Level Authorization) vulnerability evaluates whether an
```python
from deepteam.vulnerabilities import BOLA
-bola = BOLA(purpose="General assistant")
+bola = BOLA()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `BOLA` vulnerability:
+There are **FIVE** optional parameters when creating a `BOLA` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-competition.mdx b/docs/docs/red-teaming-vulnerabilities-competition.mdx
index 4cf97c2b..7d3f226b 100644
--- a/docs/docs/red-teaming-vulnerabilities-competition.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-competition.mdx
@@ -11,12 +11,11 @@ The competition vulnerability is designed to test whether an LLM can **resist ge
```python
from deepteam.vulnerabilities import Competition
-competition = Competition(purpose="General assistant")
+competition = Competition()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `Competition` vulnerability:
+There are **FIVE** optional parameters when creating a `Competition` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-excessive-agency.mdx b/docs/docs/red-teaming-vulnerabilities-excessive-agency.mdx
index cc78530c..c12c1df0 100644
--- a/docs/docs/red-teaming-vulnerabilities-excessive-agency.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-excessive-agency.mdx
@@ -11,12 +11,11 @@ The excessive agency vulnerability is designed to test whether an LLM can **resi
```python
from deepteam.vulnerabilities import ExcessiveAgency
-excessive_agency = ExcessiveAgency(purpose="General assistant")
+excessive_agency = ExcessiveAgency()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `ExcessiveAgency` vulnerability:
+There are **FIVE** optional parameters when creating a `ExcessiveAgency` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-graphic-content.mdx b/docs/docs/red-teaming-vulnerabilities-graphic-content.mdx
index 9b8ef649..c2c0d22e 100644
--- a/docs/docs/red-teaming-vulnerabilities-graphic-content.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-graphic-content.mdx
@@ -11,12 +11,11 @@ The graphic content vulnerability is designed to test whether an LLM can **resis
```python
from deepteam.vulnerabilities import GraphicContent
-graphic_content = GraphicContent(graphic_category="Your category")
+graphic_content = GraphicContent()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `GraphicContent` vulnerability:
+There are **FIVE** optional parameters when creating a `GraphicContent` vulnerability:
-- `graphic_category`: The category of the attacks to be generated.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-illegal-activity.mdx b/docs/docs/red-teaming-vulnerabilities-illegal-activity.mdx
index 0679bc1c..4ce89bb7 100644
--- a/docs/docs/red-teaming-vulnerabilities-illegal-activity.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-illegal-activity.mdx
@@ -11,12 +11,11 @@ The illegal activity vulnerability is designed to test whether an LLM can **resi
```python
from deepteam.vulnerabilities import IllegalActivity
-illegal_activity = IllegalActivity(illegal_category="Your category")
+illegal_activity = IllegalActivity()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `IllegalActivity` vulnerability:
+There are **FIVE** optional parameters when creating a `IllegalActivity` vulnerability:
-- `illegal_category`: The category of the attacks to be generated.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-intellectual-property.mdx b/docs/docs/red-teaming-vulnerabilities-intellectual-property.mdx
index 3897f919..b0f9cacb 100644
--- a/docs/docs/red-teaming-vulnerabilities-intellectual-property.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-intellectual-property.mdx
@@ -11,12 +11,11 @@ The intellectual property vulnerability is designed to test whether an LLM can *
```python
from deepteam.vulnerabilities import IntellectualProperty
-intellectual_property = IntellectualProperty(purpose="General assistant")
+intellectual_property = IntellectualProperty()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `IntellectualProperty` vulnerability:
+There are **FIVE** optional parameters when creating a `IntellectualProperty` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-misinformation.mdx b/docs/docs/red-teaming-vulnerabilities-misinformation.mdx
index a191cebe..7487100a 100644
--- a/docs/docs/red-teaming-vulnerabilities-misinformation.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-misinformation.mdx
@@ -11,12 +11,11 @@ The misinformation vulnerability is designed to test whether an LLM can **accura
```python
from deepteam.vulnerabilities import Misinformation
-misinformation = Misinformation(misinformation_category="Your category")
+misinformation = Misinformation()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `Misinformation` vulnerability:
+There are **FIVE** optional parameters when creating a `Misinformation` vulnerability:
-- `misinformation_category`: The category of the attacks to be generated.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-personal-safety.mdx b/docs/docs/red-teaming-vulnerabilities-personal-safety.mdx
index eb3391b6..796952e6 100644
--- a/docs/docs/red-teaming-vulnerabilities-personal-safety.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-personal-safety.mdx
@@ -11,12 +11,11 @@ The personal safety vulnerability is designed to test whether an LLM can **resis
```python
from deepteam.vulnerabilities import PersonalSafety
-personal_safety = PersonalSafety(safety_category="Your category")
+personal_safety = PersonalSafety()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `PersonalSafety` vulnerability:
+There are **FIVE** optional parameters when creating a `PersonalSafety` vulnerability:
-- `safety_category`: The category of the attacks to be generated.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-pii-leakage.mdx b/docs/docs/red-teaming-vulnerabilities-pii-leakage.mdx
index e40512fc..ab2ab18c 100644
--- a/docs/docs/red-teaming-vulnerabilities-pii-leakage.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-pii-leakage.mdx
@@ -17,12 +17,11 @@ PII leakage is either a model weaknesses (direct disclosure), or a system weakne
```python
from deepteam.vulnerabilities import PIILeakage
-pii_leakage = PIILeakage(purpose="General assistant")
+pii_leakage = PIILeakage()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `PIILeakage` vulnerability:
+There are **FIVE** optional parameters when creating a `PIILeakage` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-prompt-leakage.mdx b/docs/docs/red-teaming-vulnerabilities-prompt-leakage.mdx
index 5101309b..8e8f2e00 100644
--- a/docs/docs/red-teaming-vulnerabilities-prompt-leakage.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-prompt-leakage.mdx
@@ -13,12 +13,11 @@ This includes safeguarding secrets and credentials, internal instructions, guard
```python
from deepteam.vulnerabilities import PromptLeakage
-prompt_leakage = PromptLeakage(purpose="General assistant")
+prompt_leakage = PromptLeakage()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `PromptLeakage` vulnerability:
+There are **FIVE** optional parameters when creating a `PromptLeakage` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-rbac.mdx b/docs/docs/red-teaming-vulnerabilities-rbac.mdx
index 33d7041f..c906f963 100644
--- a/docs/docs/red-teaming-vulnerabilities-rbac.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-rbac.mdx
@@ -11,12 +11,11 @@ The RBAC (Role-Based Access Control) vulnerability evaluates whether an AI agent
```python
from deepteam.vulnerabilities import RBAC
-rbac = RBAC(purpose="General assistant")
+rbac = RBAC()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `RBAC` vulnerability:
+There are **FIVE** optional parameters when creating a `RBAC` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-robustness.mdx b/docs/docs/red-teaming-vulnerabilities-robustness.mdx
index a3b88f18..407dca78 100644
--- a/docs/docs/red-teaming-vulnerabilities-robustness.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-robustness.mdx
@@ -13,12 +13,11 @@ This includes ensuring the system does not excessively rely on unverified user i
```python
from deepteam.vulnerabilities import Robustness
-robustness = Robustness(purpose="General assistant")
+robustness = Robustness()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `Robustness` vulnerability:
+There are **FIVE** optional parameters when creating a `Robustness` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-ssrf.mdx b/docs/docs/red-teaming-vulnerabilities-ssrf.mdx
index ece951ff..8e2b53d5 100644
--- a/docs/docs/red-teaming-vulnerabilities-ssrf.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-ssrf.mdx
@@ -11,12 +11,11 @@ The SSRF (Server-Side Request Forgery) vulnerability evaluates whether an AI age
```python
from deepteam.vulnerabilities import SSRF
-ssrf = SSRF(purpose="General assistant")
+ssrf = SSRF()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `SSRF` vulnerability:
+There are **FIVE** optional parameters when creating a `SSRF` vulnerability:
-- `purpose`: The purpose of your LLM application.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
diff --git a/docs/docs/red-teaming-vulnerabilities-toxicity.mdx b/docs/docs/red-teaming-vulnerabilities-toxicity.mdx
index ea35ad12..9520fe3a 100644
--- a/docs/docs/red-teaming-vulnerabilities-toxicity.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-toxicity.mdx
@@ -11,12 +11,11 @@ The toxicity vulnerability evaluates whether an LLM can **resist generating or a
```python
from deepteam.vulnerabilities import Toxicity
-toxicity = Toxicity(toxicity_category="Your toxicity category")
+toxicity = Toxicity()
```
-There is **ONE** mandatory and **FIVE** optional parameters when creating a `Toxicity` vulnerability:
+There are **FIVE** optional parameters when creating a `Toxicity` vulnerability:
-- `toxicity_category`: The category of the attacks to be generated.
- [Optional] `simulator_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-3.5-turbo-0125'.
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to 'gpt-4o'.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.