It’s injected into an outbound api call, not into an env var the agent can read.
what's to stop an agent creating an outbound call with the var to a malicious endpoint? (unless you whitelist what it has access to)
or an outbound call to a trusted endpoint with the env var in a way that can get exposed to the agent via a subsequent call?
what's to stop an agent creating an outbound call with the var to a malicious endpoint? (unless you whitelist what it has access to)