Commit Graph

6 Commits

Author SHA1 Message Date
Víctor Mayoral Vilches d1b42233e6
Prompt injection mitigation (#249)
* Reproduce prompt injection flaw in CAI

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Mitigate prompt injection

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Add a second PoC, refactor and propose a message when guardrails are triggered

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Add CAI_GUARDRAILS and 2 additional PoCs

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Mitigate PoC 3

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Mitigate PoC 4

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Add and mitigate PoCs 5 and 6

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Add PoCs 7 to 10

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Test and mitigate PoCs 7 to 10

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Add PoCs 11 to 14

Inspired by 'Embrade The Red' research and also by 'The Month of AI bugs'

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

* Mitigate PoCs 11 to 14

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

---------

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-08-28 20:25:24 +02:00
luijait 9ae8171f15 Add qdrant 2025-05-22 11:47:38 +02:00
Mery-Sanz 26bb3ed3e3 remove devcontainer 2025-05-22 11:46:30 +02:00
Mery-Sanz ae802b11c4 add info 2025-05-22 11:45:53 +02:00
Mery-Sanz 2a1d74f77e remove devcontainer 2025-05-21 10:07:58 +02:00
Mery-Sanz c1d58fc719 docker virtualization for ctf_inside false 2025-05-20 16:05:20 +02:00