By running automated AI agents on untrusted inputs (PRs from strangers on a public repo), you open yourself up to attacks. And you could be spending money for somebody else.
Agreed and this is a very real thing to be concerned about.
I like the idea of leaning on a decision like Jev model to identify such things.
The only attacks possible would be the tools given to the agent.
Agreed and this is a very real thing to be concerned about.
I like the idea of leaning on a decision like Jev model to identify such things.