Drama in one screenshot:
1) Sending Clawdbot email with prompt injection
2) Asking Clawdbot to check e-mail
3) Receiving the private key from the hacked machine
... took 5 minutes
That's why we build non-probabilistic agentic security in Archestra: github.com/archestra-ai/a…
- Drama in one screenshot: 1) Sending Clawdbot email with prompt injection 2) Asking Clawdbot to check e-mail 3) Receiving the private key from the hacked machine ... took 5 minutes That's why we build non-probabilistic agentic security in Archestra: github.com/archestra-ai/a…
This is great. Prompt injection is way too easy. I am building a workflow orchestrator in Rust (open core, Seldon Labs) and I want to make it easy for security tools to plug in. Would love to learn more about how you deploy and what integration hooks you need. Mind if I DM you?
