|
|
|
|
|
|
by ildari
252 days ago
|
|
|
Most mcp endpoints don’t run any models, the main model decides which tools the ai agent should execute, and if the agent passes results back into context, that opens the door to prompt injections. It’s really a cat-and-mouse game, where for each new model version, new jailbreaks and injections are found |
|
|