Detect when your AI agent copies a self-replicating prompt injection

T1Covered by 1 source · first reported by Docker / HashiCorp / Grafana / Datadog / Honeycomb / Fly.io at 29 Oct, 00:00 UTC

Learn how Datadog AI Guard can flag self-replicating prompt injections when an AI agent copies hidden instructions into email replies or skill files.

Sources

• T1Detect when your AI agent copies a self-replicating prompt injectionDocker / HashiCorp / Grafana / Datadog / Honeycomb / Fly.io29 Oct, 00:00