Prompt Injection Report prompt injection · the report rev.2026.06
// Lab log archive
Every prompt is hostile input.
A focused publication on prompt injection. Direct and indirect techniques, model-specific behaviors, taxonomy, PoCs against open and closed models, defenses and their failure modes — written for working AI red teamers, not press releases.
Enter the archive →Latest entries
// index10 entries
OWASP LLM Top 10 Prompt Injection (LLM01:2025): What AppSec Teams Need to Know
Standards & Frame…How Prompt Injection Attacks Work: Direct, Indirect, and Agent Hijacking
Attack TechniquesInvisible Prompt Injection: The Unicode Tag Smuggling Technique
offensiveAnatomy of a Real Prompt Injection: The Bing Chat / Sydney Case
incidentGarak vs. PyRIT vs. promptmap: Prompt Injection Testing Compared
toolingRebuff Defense Review: What It Catches and Where It Fails
defenseIndirect Prompt Injection Against a Llama 3 RAG Pipeline: How the Attack Classes Work
offensiveA Working Taxonomy of Prompt Injection Attack Types
primerPrompt Injection vs. Jailbreaking: Two Conflated Attack Classes
primerPrompt Injection as Regulatory Failure: Deployer Liability
policy
Why trust us
Trusted by researchers across the AI security community
Prompt Injection Report is part of a 26-site editorial network covering adversarial ML, AI governance, defensive tooling, and ops engineering — all open access.
26
Sites in network
Across 6 topic clusters
400+
Expert articles
And growing daily
Daily
New content
Automated + editorial
Free
Always free to read
Newsletter included
Subscribe
Prompt Injection Report — in your inbox
Prompt injection PoCs, taxonomy, and primary sources. — delivered when there's something worth your inbox.
No spam. Unsubscribe anytime.