RESEARCH

Research & Intelligence

Four streams of published work from active engagements — sanitized findings, named vulnerabilities, no client data. We publish what we learn so the field gets safer, faster.

SUBSCRIBE TO BRIEFINGS →
// THREAT REPORT 0008 · MAY 202618 min read · 22 pages
RAG weaponizationprompt injectionindirect injection

Indirect Prompt Injection 2026: A Field Survey

Six months of production telemetry across 40+ AI deployments. How automated scrapers are weaponizing RAG pipelines against internal LLMs, and the three defensive patterns that actually work.

// THE AGENTIC THREAT LANDSCAPE
Living document · updated quarterly

A continuously updated map of the attack patterns we see emerging across multi-agent, RAG, and tool-calling AI systems. Less a paper, more a worldview.

// LANDSCAPE
2026
Last updated: MAY 2026Q2 update

The 2026 Agentic Threat Landscape

Across Q1–Q2 2026, we've seen the attack surface shift decisively toward multi-agent privilege escalation, indirect injection via tool outputs, and supply-chain attacks on shared agent frameworks. This living document tracks what we're seeing, what we expect next, and how defenders should prioritize.

  • 1. Multi-agent privilege escalation
  • 2. Indirect injection via tool outputs
  • 3. Agent framework supply chain
  • 4. RAG perimeter degradation

Get research before it goes public

One email per month. New threat reports, vulnerability disclosures the moment they're published, and pre-release access to upcoming papers. Unsubscribe anytime.

Updated continuously · Sanitized findings · No client names · Under NDA on every engagementOPEN A RESEARCH COLLABORATION →