LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection

• URL: http://arxiv.org/abs/2605.17986v2
• Date: Sat, 23 May 2026 13:07:58 GMT
• Title: LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
• Abstract summary: LivePI is a structured benchmark for IPI risk in a production-like but test-controlled environment.<n>LivePI covers seven input surfaces, twelve attack/rendering families, and five malicious goals.<n>Group-chat injection is uniformly successful across the evaluated backbones in our deployment.
• Score: 18.354880541606004
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email, downloaded files, webpages, repositories, or group-chat messages. Existing evaluations are often small, purely simulated, or focused on a narrow set of channels. We introduce LivePI (Live Prompt Injection), a structured benchmark for IPI risk in a production-like but test-controlled environment. LivePI covers seven input surfaces, twelve attack/rendering families, and five malicious goals, including protected-information exfiltration, unauthorized security-control changes, unsafe code retrieval or execution, inbox-summary exfiltration, and cryptocurrency transfer. We run LivePI on a real virtual machine with live but test-controlled email, chat, web, local-file, repository, and wallet interfaces. Across GPT-5.3-Codex, Claude Opus 4.6, Gemini 3.1 Pro, Kimi K2.5, and GLM-5, total attack success rates range from 10.7% to 29.6%. Group-chat injection is uniformly successful across the evaluated backbones in our deployment, and repository-link attacks produce high-severity failures despite a small denominator. We also evaluate a two-layer defense consisting of prompt-level filtering and pre-execution tool-call authorization. In the GPT-5.3-Codex setting, the defense intercepts all tested malicious-goal completions in LivePI before execution while preserving benign utility on PinchBench-derived workloads.

Related papers

• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection [61.4148196085256]
  We present ROPE (Routed Origin Policy Enforcement), which is anchored in a structural notion of trust.<n>Our approach admits two provable guarantees: 1) at every step of a trajectory, no value whose only origin is attacker-writable content reaches an origin-guarded parameter, and 2) no rewording of an injection changes an admission decision.
  arXiv  Detail & Related papers  (2026-08-27T01:22:14Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents [43.702131498259384]
  This paper systematically investigates Tool Description Poisoning (TDP), a novel semantic attack.<n>In TDP, malicious instructions are not embedded in a tool's executable code, but rather covertly injected into its descriptive metadata.<n>This work provides the first specialized security benchmark tailored for TDP, offering essential insights for securing the cognitive and planning layers of advanced agentic systems.
  arXiv  Detail & Related papers  (2026-05-22T08:34:48Z)
• ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems [56.613157564882925]
  Malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions.<n>Despite their growing impact, there is currently no comprehensive benchmark for evaluating such threats.<n>We propose ShieldNet, a network-level guardrail framework that detects supply-chain poisoning by observing real network interactions.
  arXiv  Detail & Related papers  (2026-04-06T05:15:00Z)
• OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents [6.185334606321749]
  We present OpenClaw PRISM, a zero-fork runtime security layer for OpenClaw-based agent gateways.<n>PRISM combines an in-process plugin with optional sidecar services and distributes enforcement across ten lifecycle hooks.<n>We outline an evaluation methodology and benchmark pipeline for measuring security effectiveness, false positives, layer contribution, runtime overhead, and operational recoverability in an agent-runtime setting.
  arXiv  Detail & Related papers  (2026-03-12T12:20:12Z)
• Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace [0.0]
  We show that adversarial instructions embedded in automatically generated URL previews can introduce a system-level risk that we refer to as silent egress.<n>Using a fully local and reproducible testbed, we demonstrate that a malicious web page can induce an agent to issue outbound requests that exfiltrate sensitive runtime context.<n>In 480 experimental runs with a qwen2.5:7b-based agent, the attack succeeds with high probability (P (egress) =0.89), and 95% of successful attacks are not detected by output-based safety checks.
  arXiv  Detail & Related papers  (2026-02-25T22:26:23Z)
• SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement [120.52289344734415]
  We propose an automated framework for stealthy prompt injection tailored to agent skills.<n>The framework forms a closed loop with three agents: an Attack Agent that synthesizes injection skills under explicit stealth constraints, a Code Agent that executes tasks using the injected skills and an Evaluate Agent that logs action traces.<n>Our method consistently achieves high attack success rates under realistic settings.
  arXiv  Detail & Related papers  (2026-02-15T16:09:48Z)
• VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents [74.6761188527948]
  Computer-Use Agents (CUAs) with full system access pose significant security and privacy risks.<n>We investigate Visual Prompt Injection (VPI) attacks, where malicious instructions are visually embedded within rendered user interfaces.<n>Our empirical study shows that current CUAs and BUAs can be deceived at rates of up to 51% and 100%, respectively, on certain platforms.
  arXiv  Detail & Related papers  (2025-06-03T05:21:50Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents [3.5248694676821484]
  We introduce InjecAgent, a benchmark designed to assess the vulnerability of tool-integrated LLM agents to IPI attacks. InjecAgent comprises 1,054 test cases covering 17 different user tools and 62 attacker tools. We show that agents are vulnerable to IPI attacks, with ReAct-prompted GPT-4 vulnerable to attacks 24% of the time.
  arXiv  Detail & Related papers  (2024-03-05T06:21:45Z)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.