Nanotech seems to be smaller risk than AI or biotech, but it advanced form has many ways of omnicide. Nanotech will be probably created after strong biotech, but short before strong AI (or by AI), so the period of vulnerability is rather short. Anyway nanotech has different stages it its future development, mostly dependent on its level of miniaturisation and ability to replicate. To control it in the future will be build some kind of protection shield which may have its own failure modes.
The main reading about the risk is Freitas's article "Some limits to global ecophagy by biovorous nanoreplicators" and "Nanoshield".
Some integration between bio and nanotech has already started in the form of DNA-origami. So may be first nanobots will be bionanobots, like upgraded version of E.coli.
Pdf is here: http://immortality-roadmap.com/nanorisk.pdf
It seems nano-toxicity is also about the ability to cross the blood/brain barrier. If some particles trigger the same toxicity dampening effects that the Alzheimers plaques try to implement, inflammation will continue to damage the brain and it's electrochem interactions. Brain as grey-goo
http://www.alz.org/braintour/plaques.asp
it also seems like you haven't included prions in your graph. A prion in the wild is a possible template for self replication of another protein, that may have horrid outcomes. It is also pretty simple to see distribution in the food network, perhaps as a food color, as an easy, and accidental distribution method
edit Seems like you haven't read Ringworld, or you would have some worse considerations of a specific carbon cutting organism released to the atmosphere. For instance, what if something was developed that only cut the O-O bond , in particular, that CO2 would get a lot deadlier....
I think that all kinds of nanoparticles are appearing naturally in the form of smoke and dust. It is known to be unhealthy, but nothing like existential risk. Smoking cigarets is known to damage brain, but it is not a grey goo.
I included prions in another my map biological risks, here: http://lesswrong.com/r/discussion/lw/nbw/the_map_of_global_catastrophic_risks_connected/