Product
Unplug AI
Unplug is agent runtime security for LLM applications. It tracks where text came from (user vs retrieved vs tool output), scans for prompt injection and destructive actions, and enforces tool-call policy, with span-level…
About
Unplug is agent runtime security for LLM applications. It tracks where text came from (user vs retrieved vs tool output), scans for prompt injection and destructive actions, and enforces tool-call policy, with span-level redaction instead of binary blocking. Most guardrails nuke the whole message. Unplug finds the exact attack span and surgically removes it, keeping the rest usable.
Discovery history
- Product Hunt 新品
Discuss this product