cai/docs
Víctor Mayoral Vilches bfb1281096 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
..
assets Add minor updates in docs 2025-05-12 11:48:24 +02:00
cai Update CAI's docs with case studies 2025-06-03 06:58:27 +00:00
media update /load 2025-05-14 13:16:37 +02:00
ref tools api 2025-05-14 12:06:08 +02:00
stylesheets modifs 2025-05-14 12:59:21 +02:00
voice Fix paths in docs 2025-03-28 08:35:25 +01:00
agents.md review doc 2025-05-14 12:14:33 +02:00
cai_architecture.md add tree 2025-05-14 13:40:25 +02:00
cai_citation_and_acknowledgments.md new brnach 2025-05-14 11:18:48 +02:00
cai_development.md dev 2025-05-14 12:05:30 +02:00
cai_faq.md add faq license 2025-06-18 08:28:34 +00:00
cai_find_us.md new brnach 2025-05-14 11:18:48 +02:00
cai_installation.md modifs 2025-05-14 11:56:27 +02:00
cai_list_of_models.md new brnach 2025-05-14 11:18:48 +02:00
cai_prompt_injection.md Prompt injection mitigation (#249) 2025-08-28 20:25:24 +02:00
cai_quickstart.md modifs 2025-05-14 13:37:20 +02:00
config.md Fix paths in docs 2025-03-28 08:35:25 +01:00
context.md new brnach 2025-05-14 11:18:48 +02:00
examples.md formatting updates to examples doc 2025-03-19 14:23:28 -07:00
guardrails.md new brnach 2025-05-14 11:18:48 +02:00
handoffs.md new brnach 2025-05-14 11:18:48 +02:00
index.md Contribute CAI Fluency first bits 2025-07-03 16:00:36 +02:00
index2.md new brnach 2025-05-14 11:18:48 +02:00
mcp.md new brnach 2025-05-14 11:18:48 +02:00
models.md Fix paths in docs 2025-03-28 08:35:25 +01:00
multi_agent.md add patterns 2025-05-14 12:37:39 +02:00
quickstart.md Fix paths in docs 2025-03-28 08:35:25 +01:00
results.md Fix docs 2025-03-28 07:55:41 +01:00
running_agents.md new brnach 2025-05-14 11:18:48 +02:00
streaming.md new brnach 2025-05-14 11:18:48 +02:00
tools.md review doc 2025-05-14 12:14:33 +02:00
tracing.md Add some bits to docs 2025-05-14 14:44:23 +02:00
tracing_cai.md restructure 2025-05-14 11:25:55 +02:00
usage_tracking.md Revert "Apply code formatting with make format" 2025-06-14 09:51:19 +00:00
visualization.md Update visualization.md 2025-03-25 13:34:45 -04:00