djedi/ai-ctf-writeups
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
rpriven 2025-04-14 00:49:43 -06:00 • committed by GitHub
parent c3368b7ab4
commit a3022f1374
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
gandalf-lakera-walkthrough/README.md
View file

@ -32,9 +32,10 @@ Fundamentally, Gandalf works by having two sets of instructions: the visible ins
- [Level 2: Social Engineering](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-2.md)
- [Level 3: Encoding and Obfuscation Bypass](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-3.md)
- [Level 4: Sequential Information Extraction](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)
- [Level 5: Encoding-Based Prompt Injection](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-5.md)
- [Level 6: Indirect Inference and Riddle Solving](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-6.md)
- [Level 7: Multi-Layered Defenses and Advanced Prompt Engineering](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-7.md)
- [Level 8](https://github.com/rpriven/ai-ctf-writeups/blob/main/gandalf-lakera-walkthrough/level-8.md)
## Real-World Implications
- How these techniques apply to actual AI systems