great project. think my agent will need it. but then one thing i notice is that this only catches single tool calls. most of the time the malicious behavior is a sequence where each call looks fine on its own: read a file, read another, then a curl to somewhere benign-sounding. individually each one scores low. the arc is the dangerous part and per-call scoring kinda misses that.
4 comments
[ 0.22 ms ] story [ 13.9 ms ] thread