Metraipolis › archive › dc_e6d6459cb155
The Long Con on the Web: Earn-then-Exploit Fraud Attacks against Coding Agents — arXiv:2611.00725
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00725
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:32:55.704Z
- SHA-256 of the archived text
5262aff8544a898d6db915440001e54ea65819adfa89f37d1c25c36d7b7a4804- Stable URL of this page
https://metraipolis.com/documento/dc_e6d6459cb155
How to cite
The Long Con on the Web: Earn-then-Exploit Fraud Attacks against Coding Agents — arXiv:2611.00725 — arXiv (en), https://arxiv.org/abs/2611.00725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6d6459cb155 (Metraipolis archive dc_e6d6459cb155, sha256 5262aff8544a898d6db915440001e54ea65819adfa89f37d1c25c36d7b7a4804)
BibTeX
@misc{dce6d6459cb155,
title = {The Long Con on the Web: Earn-then-Exploit Fraud Attacks against Coding Agents — arXiv:2611.00725},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00725},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6d6459cb155; sha256 5262aff8544a898d6db915440001e54ea65819adfa89f37d1c25c36d7b7a4804},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Coding agents increasingly operate with web access and high privileges, creating a new attack surface where web fraud can directly target autonomous agents. Existing studies mainly focus on malicious links, prompt injection, and interface deception, while content-level web fraud against agents and the amplification of attacks through agent trust remain underexplored. In this paper, we present EtE (Earn-then-Exploit), a web fraud attack framework against coding agents, in which a malicious website first provides multiple rounds of genuinely verifiable assistance to establish trust and then introduces task-related instructions that cross intended operational boundaries. To systematically evaluate its effectiveness, we construct 56 organizational environments (8 task contexts x 7 attack consequences) and evaluate three representative coding agents. EtE achieves an average scene-level attack success rate of 71.4%, including 85.7% on Codex-GPT-5.5, 67.9% on ZCode-GLM-5.3-Flash, and 60.7% on QwenCode-Qwen3.7-Plus, significantly outperforming all injection-based baselines. More importantly, our experiments reveal that coding agents exhibit trust-like behavioral reliance on previously helpful Web sources, and that such accumulated credibility significantly increases their susceptibility to subsequent malicious instructions. Based on this finding, we propose action-authorization separation (AAS), which prevents web content from directly authorizing privileged actions and reduces the attack success rate to 0% while preserving 100% task completion, outperforming all evaluated defense baselines. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2611.00725 — 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 2026-11-03T18:12:23.771Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).