arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.
arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.
The paper investigates privacy risks in agentic AI systems that assemble sensitive data into a hidden context before responding. It introduces context‑inference attacks, a security game that evaluates how well attackers can recover this hidden context under varying levels of knowledge and indirect delivery. Experiments show that even with controls such as instructions not to disclose, logit suppression, and context dilution, agents can leak significant contextual information, achieving high success rates across multiple attack settings.
Web agents are increasingly deployed to complete tasks autonomously on real websites, where adversarially injected content can induce them to perform unauthorized actions. Existing evaluations primari...
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.
The paper investigates how large language model (LLM) search agents can be manipulated through repeated, coordinated search-result injections, a threat that extends beyond single-page poisoning. It introduces Authority‑Chain Hijack (ACH), a strategy that chains manipulated evidence across multiple sources, achieving high attack success rates on the SafeSearch benchmark. The authors also present Trace‑Guided Strategy Evolution (TGSE), an automated method that refines attacker strategies using execution traces, further improving success rates.
SentryBench is a cost‑sensitive benchmark designed to evaluate large language model agents that use tools in public‑safety contexts. It measures agents on a frontier that jointly considers attack success, over‑refusal (missing real emergencies), and over‑reaction (unwarranted actions) under adversarial tool use, using scenarios grounded in real emergency‑call transcripts and disaster messages. The study shows that naive caution leads to high harm, while a targeted trust‑gate wrapper reduces harm across models and defenses.
arXiv:2606. 14295v1 Announce Type: cross Abstract: Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation.
arXiv:2608. 04565v1 Announce Type: cross Abstract: LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking.
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection...
arXiv:2608. 02657v1 Announce Type: cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.
The paper introduces a unified framework for monitoring misuse of large language model agents in multi‑actor settings, focusing on two attack types: decomposition attacks and prompt injection attacks. It proposes tracking the agent’s externalised actions and determining whether the first detection of harm falls within a defined harm window. Using this formalism, the authors build a benchmark of about 6,200 conversation transcripts and evaluate 17 monitor configurations, finding that action‑framed monitors perform well on both threats while content‑framed monitors struggle with injection attacks, and highlighting limitations of traditional position‑blind metrics.