About Prompt Injection Report
Prompt Injection Report is a focused publication on OWASP LLM01. Coverage runs across four lines: the attack side, meaning a five-class taxonomy, the channels indirect injection arrives through, Unicode Tag smuggling, and documented cases such as the Bing Chat / Sydney incident; the detection side, meaning what each detector family catches and the bypasses published against it; the testing side, meaning a repeatable method plus the tooling landscape of Garak, PyRIT, promptmap and the public benchmarks; and the deployer side, meaning layered defences in implementation order and the regulatory question of who is liable when an injection succeeds.
It is written for AI red teamers and application developers. Every technique is tied to a published paper, advisory, or public proof of concept, and the site does not present unverified attacks as reproduced.
What is covered here
- Defense
- Explainer
- Incident
- Offensive
- Policy
- Primer
- Standards & Frameworks
- Tooling
13 articles are published so far. New articles are announced on the RSS feed; there is no fixed publishing schedule and this site does not promise one.
Start here
Four pages carry most of the reference material, and everything else links back into them:
- How prompt injection attacks work — the five-class taxonomy the rest of the site is organised around
- Indirect prompt injection — the channels a payload arrives through and what the published benchmarks measure
- Detection techniques — what each detector family catches, and the bypass documented against each one
- Testing method — scoping assertions, choosing a corpus and harness, and scoring attack success rate as a tracked number
There is also one interactive tool: the injection threat modeler. Select the building blocks your application actually contains — retrieval, browsing, tools, memory, file upload, multi-modal input — and it returns the taxonomy classes those blocks make reachable, the trust boundary each one crosses, and the defences that apply. It runs entirely in the browser and describes sanitised attack patterns only, never live payloads.
How these articles are produced
Articles are researched from primary sources: vendor and project documentation, published standards and specifications, release notes, advisories, and measurements published by the people who took them. Drafts are produced with AI assistance and then edited against those same sources before anything is published. Where a figure comes from a datasheet or a third-party measurement, the article names the source and links to it so you can check the original rather than take this site's summary of it.
Everything here is published under the Prompt Injection Report Editorial byline. That is an editorial desk, not a person, and no article on this site claims hands-on lab testing, benchmarking, or first-hand measurement. Nothing here should be read as a report of something this site physically tested.
Corrections
Getting it right matters more than getting it first. If something on this site is wrong, out of date, or missing the source it should cite, email hello@promptinjection.report with the page and the specific claim. Substantive corrections are made on the page itself rather than quietly dropped.
How this site is funded
This site currently runs no affiliate links, no sponsored content, no paid placement, and no display advertising. Nothing on it earns a commission. If that changes, this page and the disclosure page will say so before any such link appears.
The full position is on the disclosure page. Read it before acting on anything here that reads like a buying recommendation.
Related sites
Prompt Injection Report is run alongside a small number of other single-topic sites:
- Adversarial ML - Working adversarial ML — exploits, defenses, and the gap between.
- AI Attacks - Practitioner-grade AI red team techniques and tooling.
- AI Sec - Offensive AI security — prompt injection, jailbreaks, agent exploitation, red team writeups.
- JailbreakDB - An indexed catalog of working LLM jailbreak techniques.
- Jailbreaks FYI - Working LLM jailbreak techniques, sourced and dated.
Contact
Email: hello@promptinjection.report
Site: promptinjection.report
Privacy: privacy policy ·
terms of use