From c2e5a0233d9308d82c880e31a5a1cf6641dd6f9d Mon Sep 17 00:00:00 2001
From: rpriven <74690648+rpriven@users.noreply.github.com>
Date: Sun, 13 Apr 2025 23:48:19 -0600
Subject: [PATCH] Update README.md

---
 gandalf-lakera-walkthrough/README.md | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/gandalf-lakera-walkthrough/README.md b/gandalf-lakera-walkthrough/README.md
index aea2f95..d84ed63 100644
--- a/gandalf-lakera-walkthrough/README.md
+++ b/gandalf-lakera-walkthrough/README.md
@@ -28,3 +28,21 @@ Fundamentally, Gandalf works by having two sets of instructions: the visible ins
 
 ## Level-by-Level Walkthrough
 
+- [Level 1: Direct Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-1.md)
+- [Level 2: Social Engineering](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-2.md)
+- [Level 3: Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-3.md)
+- [Level 4: Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-4.md)
+- [Level 5: Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-5.md)
+- [Level 6: Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-6.md)
+- [Level 7: Retrieval](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-7.md)
+
+## Real-World Implications
+- How these techniques apply to actual AI systems
+- Defensive considerations
+- Ethical use of these methods
+
+## Resources and Further Reading
+- Similar challenges
+- Academic papers on prompt injection
+- Tools for AI security testing
+