RESEARCH

Prompt Injection in Production: What We Found Red-Teaming Enterprise LLM Deployments

AI SECURITY LAB · 12 MIN READ · ZENC LABS RESEARCH · 2026

Prompt injection has held the #1 position in the OWASP Top 10 for LLM Applications since the list was created, and across our red-team engagements, it remains the vulnerability class we exploit most reliably. The uncomfortable finding: most enterprise LLM deployments are tested like software, but attacked like people. Traditional AppSec testing barely touches the failure modes that matter.

▲ OWASP LLM01: PROMPT INJECTION · AI-SPECIFIC CVEs UP 2,000%+ SINCE 2022 · MOST EXPLOITED SURFACE: RAG PIPELINES

The three patterns that keep working

1. Indirect injection through retrieval. The copilot doesn't need to trust the user, it trusts the documents. Payloads planted in a shared drive, a support ticket, an inbound email, or a scraped web page get retrieved into context and executed as instructions. In RAG-heavy deployments this is consistently the softest entry point, because content-ingestion pipelines were never designed as trust boundaries.

2. Privilege inheritance. LLM applications frequently run with the union of all users' permissions rather than the caller's. When an assistant can query the data warehouse, the question "summarize everything you can see about executive compensation" becomes an access-control bypass, no exploit code required.

3. Tool-chain escalation. Agentic deployments that can send email, file tickets, or call APIs convert a text vulnerability into an action vulnerability. A single injected instruction in a low-trust input can trigger a high-trust action downstream.

The guardrails that held

The executive takeaway: prompt injection is not a bug you patch, it is a property of instruction-following systems that you architect around. Budget for containment, not elimination.

How we test

ZenC Labs engagements map every finding to OWASP LLM Top 10 and MITRE ATLAS technique IDs, replay attack chains against staging with your engineers watching, and deliver fixes ranked by exploitability, not a severity-score spreadsheet. Typical engagement: two weeks from scoping to executive readout.

SOURCES: OWASP Top 10 for LLM Applications 2025 · MITRE ATLAS · NIST AI RMF · ZenC Labs engagement methodology

Shipping an AI feature this quarter?

Get it adversarially tested before your customers, or an attacker, do it for you.

Talk to the AI Security Lab