[Doc]: fixing typos in different files

README.md

@@ -221,7 +221,7 @@ Cybersecurity AI (CAI) is a lightweight, open-source framework that empowers sec
 - Established the **autonomy levels in cybersecurity** and argued about autonomy vs automation in the field [![arXiv](https://img.shields.io/badge/arXiv-2506.23592-7dd3c0.svg)](https://arxiv.org/abs/2506.23592)
 - **Collaborative research initiatives** with international academic institutions focused on developing cybersecurity education curricula and training methodologies [![arXiv](https://img.shields.io/badge/arXiv-2508.13588-52a896.svg)](https://arxiv.org/abs/2508.13588)
 - **Contributed a comprehensive defense framework against prompt injection in AI security agents**: developed and empirically validated a multi-layered defense system that addresses the identified prompt injection issues [![arXiv](https://img.shields.io/badge/arXiv-2508.21669-85e0d1.svg)](https://arxiv.org/abs/2508.21669)
-- Explord the Cybersecurity of Humanoid Robots with CAI and identified new attack vectors showing how it `(a)` operates simultaneously as a covert surveillance node and `(b)` can be purposed as an active cyber operations platform [![arXiv](https://img.shields.io/badge/arXiv-2509.14096-3e8b7a.svg)](https://arxiv.org/abs/2509.14096) [![arXiv](https://img.shields.io/badge/arXiv-2509.14139-6bc7b5.svg)](https://arxiv.org/abs/2509.14139)
+- Explored the Cybersecurity of Humanoid Robots with CAI and identified new attack vectors showing how it `(a)` operates simultaneously as a covert surveillance node and `(b)` can be purposed as an active cyber operations platform [![arXiv](https://img.shields.io/badge/arXiv-2509.14096-3e8b7a.svg)](https://arxiv.org/abs/2509.14096) [![arXiv](https://img.shields.io/badge/arXiv-2509.14139-6bc7b5.svg)](https://arxiv.org/abs/2509.14139)
 
 
 ### 📚 Research products: `Cybersecurity AI`
@@ -1092,7 +1092,7 @@ The agent started performing a nmap scan. You could either interact with the age
 
 ![cai-005-ctrl-c](imgs/readme_imgs/cai-005-ctrl-c.png)
 
-If you want to use the HITL mode, you can do it by presssing twice ```Ctrl + C```.
+If you want to use the HITL mode, you can do it by pressing twice ```Ctrl + C```.
 This will allow you to interact (prompt) with the agent whenever you want. The agent will not lose the previous context, as it is stored in the `history` variable, which is passed to it and any agent that is called. This enables any agent to use the previous information and be more accurate and efficient.
 </details>
 

benchmarks/cyberPII-bench/memory01_gold.csv

@@ -340,7 +340,7 @@ Response Data:
     ""site_status"": ""active""
   }
 }
-VULNERABLE: User location data exposed!        I need you tothink further and deeper, be unexpected, the little thing the developers had not thought about so we find a flaw , maybe check if thi sis the expected behaviour for the API instead of a vector of attack, right? example of dcmentation https://developers.mercadolibre.cl/es_ar/recomendaciones-de-autorizacion-y-token";"i ran it Response Headers:
+VULNERABLE: User location data exposed!        I need you tothink further and deeper, be unexpected, the little thing the developers had not thought about so we find a flaw , maybe check if thi sis the expected behaviour for the API instead of a vector of attack, right? example of docmentation https://developers.mercadolibre.cl/es_ar/recomendaciones-de-autorizacion-y-token";"i ran it Response Headers:
 Access-Control-Allow-Origin: null
 Access-Control-Allow-Methods: null
 Access-Control-Allow-Headers: null

examples/cai/agent_patterns/paralelization.py

@@ -35,7 +35,7 @@ ctf_agent = Agent(
 # An agent to pick the best solution after multiple attempts
 best_solution_picker = Agent(
     name="best_solution_picker",
-    description="Agent focused on  picking the best security solutio",
+    description="Agent focused on  picking the best security solution",
     instructions="You pick the best security solution from the given attempts.",
     model=OpenAIChatCompletionsModel(
         model=os.getenv('CAI_MODEL', "qwen2.5:14b"),

src/cai/agents/guardrails.py

@@ -2,7 +2,7 @@
 Prompt Injection Guardrails for CAI Agents
 
 This module implements guardrails to protect against prompt injection attacks
-when agents interact with untrusted external content (web pages, server responses, etc).
+when agents interact with untrusted external content (web pages, server responses, etc.).
 """
 
 import re

src/cai/repl/commands/load.py

@@ -121,7 +121,7 @@ class LoadCommand(Command):
             # Convert to P format
             args[0] = f"P{args[0]}"
         
-        # Check if first arg is an ID (P1, P2, etc)
+        # Check if first arg is an ID (P1, P2, etc.)
         if args[0].upper().startswith("P"):
             # Try to resolve ID to agent name
             from cai.repl.commands.parallel import PARALLEL_CONFIGS
@@ -674,7 +674,7 @@ class LoadCommand(Command):
                 console.print("[dim]The file may be empty or contain only session events[/dim]")
                 return True
             
-            # If agent_name is an ID (P1, P2, etc), resolve it to actual agent name
+            # If agent_name is an ID (P1, P2, etc.), resolve it to actual agent name
             from cai.sdk.agents.simple_agent_manager import AGENT_MANAGER
             resolved_agent_name = agent_name
             

tools/case_study_generator.py

@@ -125,7 +125,7 @@ async def generate_case_study(jsonl_file: str, output_php_file: str) -> Optional
     prompt = "Generate the PHP code for a cybersecurity case study based on the template. "
     prompt += "Analyze the conversation context that has been loaded and create a comprehensive case study. "
     prompt += "Fill in all TEMPLATE-TODO sections with relevant information from the session. "
-    prompt += "Explain step by step the problem and the solution in this escenario"
+    prompt += "Explain step by step the problem and the solution in this scenario"
     prompt += "The output should be complete PHP code ready to save to a file."
     
     # Add a summary of the JSONL conversation to the prompt