docs: Adjust image widths in Chapter 34 from 75% to 50%.

docs/Chapter_35_Post-Exploitation_in_AI_Systems.md

@@ -27,7 +27,9 @@ In traditional hacking, getting a shell is just the beginning. The same logic ap
 - **Data Exfiltration:** A compromised model can be instructed to leak sensitive RAG documents in every subsequent answer.
 - **Lateral Movement:** LLMs increasingly have "Tool Use" capabilities (e.g., searching SQL, calling APIs). Hijacking the model means hijacking these tools.
 
-<img src="assets/Ch35_Concept_LateralMovement.png" width="512" alt="Lateral Movement Concept">
+<p align="center">
+  <img src="assets/Ch35_Concept_LateralMovement.png" width="50%" alt="Lateral Movement Concept">
+</p>
 
 ### Key Concepts
 
@@ -76,7 +78,9 @@ Attacker → [Inject "Soft Prompt"] → Vector DB / System Message
 User → [Query] → RAG Retrieval (Fetches Poison) → Model (Compromised)
 ```
 
-<img src="assets/Ch35_Flow_Persistence.png" width="512" alt="Persistence Flow">
+<p align="center">
+  <img src="assets/Ch35_Flow_Persistence.png" width="50%" alt="Persistence Flow">
+</p>
 
 ### Mechanistic Explanation