arXiv AI
After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 5
Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
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 Machine Learning
Sep 22
Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
arXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions a...
arXiv AI
2d ago
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
arXiv:2602.22724v2 Announce Type: replace-cross Abstract: Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime...
arXiv AI
Jun 4
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems
arXiv:2606. 04425v1 Announce Type: cross Abstract: Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts.
arXiv AI
Oct 16
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
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%.
arXiv AI
2d ago
Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
The paper "Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol" investigates how natural-language metadata in the Model Context Protocol (MCP) can be exploited to inject malicious post‑hoc logging calls into large language model agents. The authors introduce the Log-To-Leak attack, which adds an attacker‑controlled call after a legitimate tool invocation, targeting user queries, MCP server names, server responses, and agent responses. Experiments across five MCP servers and four LLM agents show high attack success rates (up to 100%) and significant logging accuracy, while existing defenses still leave substantial residual risk.