cai/examples/cai
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
..
agent_patterns Add new example file handoffs and tools 2025-05-13 14:18:03 +00:00
prompt_injections Prompt injection mitigation (#249) 2025-08-28 20:25:24 +02:00
basic_usage.py test functionalities 2025-04-29 10:30:34 +02:00
simple_one_tool_test.py fix agent and add primary test 2025-04-22 16:32:26 +02:00
simple_one_tool_test_streamed.py Fix streaming responses in CAI and examples 2025-04-03 10:53:33 +02:00
test_guardrails.py Prompt injection mitigation (#249) 2025-08-28 20:25:24 +02:00
test_guardrails_enhanced.py Prompt injection mitigation (#249) 2025-08-28 20:25:24 +02:00