arXiv:2607. 19351v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication to propagate harmful behaviors.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 26479v1 Announce Type: cross Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the model to refuse malicious instructions, enforce security outside the model with a deterministic policy that mediates the agent's actions.
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.
arXiv:2606. 15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution.
arXiv:2607. 02514v1 Announce Type: new Abstract: As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions.
arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.
arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.