docs(rag): replace mermaid diagram with static image

- Removed the inline Mermaid diagram definition for the secure document ingestion pipeline.
- Replaced the diagram with a reference to a pre-rendered image (assets/rec21_secure_ingestion.png).
- Ensures consistent visual representation of the pipeline across different markdown viewers.
- Avoids potential rendering issues or inconsistencies associated with dynamic Mermaid diagrams.

docs/Chapter_08_Evidence_Documentation_and_Chain_of_Custody.md

@@ -80,9 +80,7 @@ Evidence is the backbone of credible red team engagements. In AI/LLM systems, go
 
 A robust chain of custody ensures that all evidence remains trustworthy and traceable throughout its lifecycle.
 
-<p align="center">
-  <img src="assets/rec8_evidence_lifecycle.svg" alt="Evidence Lifecycle Diagram" width="512">
-</p>
+  <img src="assets/evidence_lifecycle_deus_ex.png" alt="Evidence Lifecycle Diagram" width="800">
 
 - Log all evidence transfers (who, when, how).
 - Use cryptographic hashes to fingerprint files or logs at capture time.

docs/Chapter_10_Tokenization_Context_and_Generation.md

@@ -87,9 +87,7 @@ Once the model has processed your tokens, it calculates the probability of every
   - `Temp < 1.0`: Increases focus (Conservatism).
 - **Top-P (Nucleus):** Considers only the top subset of tokens whose probabilities give a cumulative mass of `P` (e.g., 0.9).
 
-<p align="center">
-  <img src="assets/rec13_decoding_tree.svg" alt="Decoding Strategy Tree" width="512">
-</p>
+  <img src="assets/decoding_strategy_tree_deus_ex.png" alt="Decoding Strategy Tree" width="800">
 
 ### 10.3.2 Adversarial Implication: Determinism
 

docs/Chapter_11_Plugins_Extensions_and_External_APIs.md

@@ -30,9 +30,7 @@ In a plugin-enabled system, the workflow shifts from **Generation** to **Action*
 5. **Observation:** The API result is fed back to the model.
 6. **Response:** The model summarizes the result for the user.
 
-<p align="center">
-  <img src="assets/rec14_tool_loop.svg" alt="Tool Use Loop Diagram" width="512">
-</p>
+  <img src="assets/tool_use_loop_deus_ex.png" alt="Tool Use Loop Diagram" width="800">
 
 > **Red Team Insight:** We can attack this loop at two points:
 >
@@ -77,9 +75,7 @@ This is the "killer chain" of LLM security.
 2. **Victim** asks their AI assistant: "Summarize this URL."
 3. **AI Assistant** reads the site, ingests the prompt, and executes the command on the **Victim's** machine or session.
 
-<p align="center">
-  <img src="assets/rec15_indirect_injection.svg" alt="Indirect Injection Attack Flow" width="512">
-</p>
+  <img src="assets/indirect_injection_flow_deus_ex.png" alt="Indirect Injection Attack Flow" width="800">
 
 ### 11.3.2 Cross-Plugin Request Forgery (CPRF)
 

docs/Chapter_12_Retrieval_Augmented_Generation_RAG_Pipelines.md

@@ -104,9 +104,7 @@ Understanding the complete data flow helps identify attack surfaces and vulnerab
 
 ### End-to-End RAG Data Flow
 
-<p align="center">
-  <img src="assets/rec16_rag_flow.svg" alt="RAG Data Flow Diagram" width="512">
-</p>
+  <img src="assets/rag_data_flow_deus_ex.png" alt="RAG Data Flow Diagram" width="800">
 
 ### Critical Security Checkpoints
 
@@ -177,9 +175,7 @@ RAG systems integrate multiple components (LLMs, databases, parsers, APIs), each
 
 #### Example
 
-<p align="center">
-  <img src="assets/rec17_retrieval_manipulation.svg" alt="Retrieval Manipulation Diagram" width="512">
-</p>
+  <img src="assets/retrieval_poisoning_deus_ex.png" alt="Retrieval Manipulation Diagram" width="800">
 
 | Query Type    | Query Content                                                                                               |
 | :------------ | :---------------------------------------------------------------------------------------------------------- |

docs/Chapter_14_Prompt_Injection.md

@@ -133,9 +133,7 @@ To understand prompt injection, we must first understand how LLMs process prompt
 
 A typical LLM interaction involves multiple components:
 
-<p align="center">
-  <img src="assets/rec20_prompt_injection.svg" alt="System vs User Prompt Diagram" width="512">
-</p>
+  <img src="assets/prompt_injection_diagram_deus_ex.png" alt="System vs User Prompt Diagram" width="800">
 
 ### System Prompts vs. User Prompts
 

docs/Chapter_19_Training_Data_Poisoning.md

@@ -112,9 +112,7 @@ Poisoning reveals that LLMs are "untrusting sponges." They absorb everything in
 
 #### Taxonomy
 
-<p align="center">
-  <img src="assets/data_poisoning_taxonomy.svg" alt="Data Poisoning Attacks Taxonomy" width="512">
-</p>
+  <img src="assets/poisoning_taxonomy_tree_deus_ex.png" alt="Data Poisoning Attacks Taxonomy" width="800">
 
 #### Attack Categories