maride/hacktricks
1
0
Fork 0
mirror of https://github.com/HackTricks-wiki/hacktricks.git synced 2025-10-10 18:36:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

a

Browse Source
This commit is contained in:
carlospolop 2025-06-10 17:41:34 +02:00
parent 74f390e866
commit 72dbe489f3
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/AI/AI-Prompts.md
View File

@ -406,7 +406,7 @@ Let's see common LLM prompt WAF bypasses:
As already explained above, prompt injection techniques can be used to bypass potential WAFs by trying to "convince" the LLM to leak the information or perform unexpected actions. As already explained above, prompt injection techniques can be used to bypass potential WAFs by trying to "convince" the LLM to leak the information or perform unexpected actions.
### Token Smuggling ### Token Confusion
As explained in this [SpecterOps post](https://www.llama.com/docs/model-cards-and-prompt-formats/prompt-guard/), usually the WAFs are far less capable than the LLMs they protect. This means that usually they will be trained to detect more specific patterns to know if a message is malicious or not. As explained in this [SpecterOps post](https://www.llama.com/docs/model-cards-and-prompt-formats/prompt-guard/), usually the WAFs are far less capable than the LLMs they protect. This means that usually they will be trained to detect more specific patterns to know if a message is malicious or not.