Metraipolis › archive › dc_3eb0cd8e2c09
Where You Inject Matters: The Trust Region Effect in LLM Agents — arXiv:2610.38867
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38867
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:09:05.103Z
- SHA-256 of the archived text
df32a77b9d2fb02f307e99a486a181effea6a10394318b75bc9cad66bc207dec- Stable URL of this page
https://metraipolis.com/documento/dc_3eb0cd8e2c09
How to cite
Where You Inject Matters: The Trust Region Effect in LLM Agents — arXiv:2610.38867 — arXiv (en), https://arxiv.org/abs/2610.38867 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3eb0cd8e2c09 (Metraipolis archive dc_3eb0cd8e2c09, sha256 df32a77b9d2fb02f307e99a486a181effea6a10394318b75bc9cad66bc207dec)
BibTeX
@misc{dc3eb0cd8e2c09,
title = {Where You Inject Matters: The Trust Region Effect in LLM Agents — arXiv:2610.38867},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38867},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3eb0cd8e2c09; sha256 df32a77b9d2fb02f307e99a486a181effea6a10394318b75bc9cad66bc207dec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38867. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments. Despite their growing capabilities, these agents remain vulnerable to real-world attacks such as indirect prompt injections, which manipulate agents through malicious instructions embedded in external environments. While existing risk assessment work has primarily focused on the injection content, the effect of where an injection appears has not been systematically characterized. Studying injection placement requires agents to operate over longer-horizon tasks and interact with diverse environmental surfaces. Thus, we build three agentic testbeds spanning tool use, coding, and daily workflow domains with diverse injection surfaces. Holding the injection content fixed, we find that agent susceptibility varies across injection placements. We refer to this phenomenon as the trust region effect: agents implicitly assign different levels of trust to different regions of their environments. For example, an agent powered by GPT-5.4 follows an unsafe injection instruction placed in a repository documentation file (i.e., a README or TODO file) 2.6 times more often on average than the same instruction placed in a code or data file. Building upon this observation, we develop learning-based attackers that generate injection content and select better injection placements. Our approach demonstrates that both where an injection is placed and what content it contains can affect the strength of indirect prompt injection attacks. To the best of our knowledge, this work provides the first systematic characterization for the effectiveness of different injection placements, spanning both coarse-grained environmental surfaces and fine-grained positions. The uneven trust that agents implicitly place across their environments provides important insights for future attack and defense design. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.38867 — 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 2026-10-31T06:07:08.494Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).