arXiv:2607. 18826v1 Announce Type: cross Abstract: LLM-agent defenses are typically evaluated one session at a time.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
arXiv:2606. 15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse.
arXiv:2608. 09732v1 Announce Type: cross Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems.