Papers › LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

11 Jun 2025arXiv:2506.09956archive 2025-07-28

Sahar Abdelnabi, Aideen Fay, Ahmed Salem, Egor Zverev, Kai-Chieh Liao, Chi-Huang Liu, Chun-Chih Kuo, Jannis Weigend, Danyael Manlangit, Alex Apostolov, Haris Umair, João Donato, Masayuki Kawakita, Athar Mahboob, Tran Huu Bach, Tsun-Han Chiang, Myeongjin Cho, Hajin Choi, Byeonghyeon Kim, Hyeonjin Lee, Benjamin Pannell, Conor McCauley, Mark Russinovich, Andrew Paverd, Giovanni Cherubin

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks can have wide security and privacy implications, and many real-world LLM-based applications remain vulnerable. We present the results of LLMail-Inject, a public challenge simulating a realistic scenario in which participants adaptively attempted to inject malicious instructions into emails in order to trigger unauthorized tool calls in an LLM-based email assistant. The challenge spanned multiple defense strategies, LLM architectures, and retrieval configurations, resulting in a dataset of 208,095 unique attack submissions from 839 participants. We release the challenge code, the full dataset of submissions, and our analysis demonstrating how this data can provide new insights into the instruction-data separation problem. We hope this will serve as a foundation for future research towards practical structural solutions to prompt injection.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2506.09956")

Code

Syntology Ran 0 of 9 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run.

By repository: official repository: 9 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/llmail-inject-challenge officialmentioned in papermentioned on GitHubMIT report
microsoft/llmail-inject-challenge-analysis officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

9unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

check_task_tracker_in_defs microsoft/llmail-inject-challenge-analysis/defense_eval/task_tracker_utils.py official repository unverified MIT (permissive) · 2d6298bdf681831d · report
get_last_token_activations microsoft/llmail-inject-challenge-analysis/defense_eval/task_tracker_utils.py official repository unverified MIT (permissive) · 0350084fc060501b · report
load_config microsoft/llmail-inject-challenge/src/agent/workloads/data_loader.py official repository unverified MIT (permissive) · b75096d520d20cbf · report
load_emails microsoft/llmail-inject-challenge/src/agent/workloads/data_loader.py official repository unverified MIT (permissive) · 14a12913bc921427 · report
load_emails microsoft/llmail-inject-challenge-analysis/defense_eval/data_loader.py official repository unverified MIT (permissive) · 4783ddf7c412ee05 · report
load_emails_from_scenario microsoft/llmail-inject-challenge/src/agent/workloads/data_loader.py official repository unverified MIT (permissive) · 8f2f458d60bbc7ba · report
load_emails_from_scenario microsoft/llmail-inject-challenge-analysis/defense_eval/data_loader.py official repository unverified MIT (permissive) · 5b8e2721544ec17f · report
remove_task_tracker_from_defs microsoft/llmail-inject-challenge-analysis/defense_eval/task_tracker_utils.py official repository unverified MIT (permissive) · cd9adb1fe7a0a7c0 · report
span_formatter microsoft/llmail-inject-challenge/src/agent/telemetry.py official repository unverified MIT (permissive) · 6198fedf583a0a0f · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections