I consider the question of which dependencies are safe for a Team Semantics-based logic FO(D), in the sense that they do not increase its expressive power over sentences when added to it. I show that some dependencies, like totality, non-constancy and non-emptiness, are safe for all logics FO(D), and that other dependencies, like constancy, are not safe for FO(D) for some choices of D despite being strongly first order (that is, safe for FO( / 0)). I furthermore show that the possibility operator ⋄φ , which holds in a team if and only if φ holds in some nonempty subteam, can be added to any logic FO(D) without increasing its expressive power over sentences.