The paper discusses the ongoing threat of prompt injection attacks on AI agents, noting that early simple attacks have plateaued but new, more capable adversaries can still succeed. It introduces a synthetic evaluation dataset that uses random non‑malicious actions as adversarial goals to test whether models respect instruction hierarchy independently of security knowledge. Experiments show that even agents considered robust on existing benchmarks can be tricked by advanced attackers, indicating that current defenses may need proactive, automated red‑teaming.
arXiv:2606. 10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings.
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:2606. 12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.
The paper introduces ReMAS, a reinforcement learning-based framework for black-box red-teaming of multi-agent systems (MAS) that fine-tunes attacker LLMs to craft adversarial prompts. ReMAS operates in two stages: a rewrite stage that refines base attack prompts to boost extraction success, and a template generation stage that builds attack templates to better invoke specific sub-agents and expose their system prompts. Experiments demonstrate that ReMAS significantly outperforms existing black-box attacks, showing high success rates and transferability across different backend LLMs and MAS structures.
INFUSE is a new benchmark that tests indirect prompt injection (IPI) in large‑language‑model agents performing long‑horizon workflows. It contains 40 realistic tasks and 56 attack scenarios across five threat categories, with attacks injected through realistic interaction surfaces rather than just initial prompts. The study evaluated 19 LLMs, generating over 41,000 adversarial trajectories and found mean attack success rates of 19.6% (LLM evaluation) and 15.4% (heuristic verification), while prompt‑level hardening reduced success from 58.2% to 14.3%.
The paper introduces T-MAP, a trajectory‑aware evolutionary search technique designed to red‑team large language model agents by exploiting vulnerabilities that arise during multi‑step tool execution. Unlike traditional methods that focus on harmful text, T‑MAP uses execution trajectories to generate adversarial prompts that bypass safety guardrails and achieve harmful objectives through actual tool interactions. Experiments across various Model Context Protocol environments show that T‑MAP outperforms baseline methods in attack realization rate and remains effective against advanced models such as GPT‑5.2, Gemini‑3‑Pro, Qwen3.5, and GLM‑5.
arXiv:2507. 22063v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) for code generation (i.
arXiv:2606. 07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop.
The paper examines how fine‑tuned defenses against prompt injection in large language models can be audited before deployment. By leveraging intermediate checkpoints from the fine‑tuning process, the authors create strong optimization‑based attacks (e.g., GCG and BEAST) that dramatically increase attack success rates—from near zero to up to 96%—against state‑of‑the‑art defenses. This demonstrates that current empirical evaluations often overestimate robustness and that pre‑deployment stress‑testing can uncover real vulnerabilities.
The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.
arXiv:2505. 14289v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) are increasingly deployed yet vulnerable to Environmental Injection Attacks (EIAs).