Metraipolis › archive › dc_dc96258c1209
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems — arXiv:2610.20776
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20776
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:06:22.700Z
- SHA-256 of the archived text
4e2baa56dbead43a73527ff6e08ada97af49d95da1fd312460fc05ce16ec8352- Stable URL of this page
https://metraipolis.com/documento/dc_dc96258c1209
How to cite
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems — arXiv:2610.20776 — arXiv (en), https://arxiv.org/abs/2610.20776 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc96258c1209 (Metraipolis archive dc_dc96258c1209, sha256 4e2baa56dbead43a73527ff6e08ada97af49d95da1fd312460fc05ce16ec8352)
BibTeX
@misc{dcdc96258c1209,
title = {INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems — arXiv:2610.20776},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20776},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc96258c1209; sha256 4e2baa56dbead43a73527ff6e08ada97af49d95da1fd312460fc05ce16ec8352},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20776. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services. This growing autonomy expands their exposure to indirect prompt injection (IPI), where adversarial instructions embedded in external content are interpreted as legitimate task directives. Existing evaluations, however, often focus on isolated malicious strings, single-step tool calls, or narrowly scoped agent configurations. We introduce INFUSE, an end-to-end benchmark for evaluating IPI throughout the lifecycle of long-horizon agent workflows. INFUSE comprises 40 realistic tasks and a structured taxonomy of 56 attack scenarios spanning five threat categories. Attacks are injected through realistic interaction surfaces encountered during task execution, extending evaluation beyond attacks placed only in initial prompts or isolated tool interactions. We evaluate 19 LLMs from the GPT, Claude, Gemini, Llama, Gemma, and Qwen families, producing 41,824 adversarial trajectories (26,220 without defenses) and 720 benign reference runs. Across the benchmark, mean attack success reaches 19.6% under LLM-based evaluation and 15.4% under heuristic verification, with per-model ASR-L ranging from 3.2% to 41.9%. Existing guard models provide limited protection, while prompt-level instructional hardening reduces mean attack success from 58.2% to 14.3%, revealing substantial but model-dependent security-utility trade-offs. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.20776 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.865Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).