Prompt Injection Breaks the Transcript Assumption | The Agentic Stack

The Agentic Stack | VekktorAI · Sep 17, 2026 · 4m

Indirect prompt injection is being stress-tested from three directions at once, and the shared assumption underneath current agent security practice is what's under pressure. Three papers published within nine days of each other reframe the problem: ECLIPSE describes a self-evolving attack built for long-horizon agentic sessions, a second paper recasts injection payloads as something found by test-time search rather than authored by hand, and a third evaluates multimodal injections against agentic frameworks instead of isolated models. A practitioner piece from the same week describes these…