Your agent's context is an attack...

Your agent's context is an attack surface

IA
Journalcast por Acidalia
E6
12 sept 2026
28:33

Notas del episodio

The agent harness as an attack surface: context assembly, the network path, crash recovery, and a defence that holds by construction.

  1. Zichuan Li, Jian Cui, Ashley Chen, Xiaojing Liao, and Luyi Xing, "What's in Your Agent's Context? Context Privilege Escalation Attacks against AI Agent Harness," arXiv:2609.01222 (2026). https://arxiv.org/abs/2609.01222
  2. Hanzhi Liu, Chaofan Shou, Hongbo Wen, Yanju Chen, Ryan Jingyang Fang, and Yu Feng, "Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain," arXiv:2604.08407 (2026). https://arxiv.org/abs/2604.08407
  3. Guanlong Wu, Dahui Li, Ke Jiang, Jianyu Niu, Cong Wang, and Yinqian Zhang, "Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback," arXiv:2608.29381 (2026). https://arxiv.org/abs/2608.29381
  4. Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan, Jamie Hayes, Nicholas Carlini, Daniel Fabian, Christoph Kern, Chongyang Shi, Andreas Terzis, and Florian Tramer, "Defeating Prompt Injections by Design," arXiv:2503.18813 (2025). https://arxiv.org/abs/2503.18813

Palabras clave

language models
AI safety