arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
arXiv:2606. 12703v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions.
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.
The paper introduces Dependency‑Tethered Memory (Tether), a memory system for tool‑using LLM agents that records the exact versions of premises each verdict depends on. By withdrawing any verdict whose support has failed anywhere in the store, Tether reduces unsafe publications to 0.3% and cuts verification calls by 37% compared to naive fact memory, while maintaining similar recall. The study demonstrates that capturing dependencies is crucial for safe memory use, as weaker writers or delayed relation arrivals increase unsafe publication rates.
arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
The paper investigates how standard evaluations of detectors for hijacked large language model (LLM) agents may conceal important weaknesses. By auditing eleven evaluations on the AgentDrift and AgentDojo benchmarks, the authors show that detectors often perform poorly when faced with rare attacks, unseen tools, or data from a different benchmark, with precision dropping dramatically at low attack rates and rankings reversing as tool coverage falls. They also find that a released LLM action monitor, despite high AUROC on its own data, would still generate many false alerts when applied to a new benchmark. "whyItMatters":"The study highlights that current evaluation practices can give a misleading sense of detector reliability, underscoring the need for more robust, cross‑benchmark testing to ensure real‑world safety of LLM agents."
arXiv:2610.17544v1 Announce Type: cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted me...
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.