Results for “Injection”

arXiv (research papers) Zimo Xu SI

CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts

Enforcement defenses against prompt injection, such as CaMeL, Progent, IPIGuard and DRIFT, ask the agent's own model to write a security artifact (a program, a privilege policy, a dependency graph or a constraint list) that code then enforces. We ask whether small language model (SLM) agents can be trusted to write these artifacts. Across 15 open-weight models, 13 of them between 1.7B and 12B parameters, they cannot: the policies, graphs and constraints that the agent's…

Read at arXiv (research papers)

arXiv (research papers) Yiheng Zhao SI

Scale-Induced Semantic Shift in Visual Prompt Injection Against VLMs and Web Agents

Visual content in multimedia systems may be resized, compressed, or re-rendered before it is interpreted by a vision-language model. We study a security failure mode in which these transformations change the machine-readable semantics of an image: a textual instruction is not recovered at a $512\times512$ presentation resolution under our evaluation protocol but becomes recoverable after aggressive downsampling. We formulate this behavior as Scale-Induced Semantic Shift…

Read at arXiv (research papers)

arXiv (research papers) Yingbin Jin Security

MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection

Mobile GUI agents read the screen of a phone and operate apps on a user's behalf to complete multi-step tasks such as online shopping or messaging. Because the agent acts on whatever the screen shows, an attacker can embed malicious instructions into ordinary UI content and redirect its actions. We refer to this threat as environmental injection attack (EIA). Existing benchmarks measure this risk by pinning hand-crafted payloads to a fixed step of a fixed task. This approach…

Read at arXiv (research papers)

arXiv (research papers) Fady Copty SI

Intent-Aware Protection for AI Agents

AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine whether an agent remains faithful to the purpose for which it was deployed. An action may contain no attack pattern and stay within granted permissions while still violating the agent's role, organizational constraints, or purpose. We introduce…

Read at arXiv (research papers)

Hacker News mooreds SI

Prompt Injection, Esq.: pwning AI agent guardrails with lawyerspeak

Article URL: https://www.mrnice.dev/posts/heavyweight-guardrails/ Comments URL: https://news.ycombinator.com/item?id=50456893 Points: 3 # Comments: 0

Read at Hacker News

CISA advisories CISA Security

CISA Adds Six Known Exploited Vulnerabilities to Catalog

CISA has added six new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-20320 Cisco BroadWorks Improper Restriction of XML External Entity Reference Vulnerability CVE-2026-111560 Barracuda Networks Multiple Products OS Command Injection Vulnerability CVE-2026-111793 Openwave Messaging Limited Webtop Media Transcoder Incorrect Resource Transfer Between Spheres Vulnerability CVE-2026-116606 Barracuda…

Read at CISA advisories

CISA advisories CISA Security

CISA Adds Four Known Exploited Vulnerabilities to Catalog

CISA has added four new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-102895 GPUStack Improper Authentication Vulnerability CVE-2026-116779 SignalWire FreeSwitch Code Injection Vulnerability CVE-2026-123158 OpenBSD OpenSSH Unexpected Status Code or Return Value Vulnerability CVE-2026-123218 IBM Aspera Faspex Incorrect Authorization Vulnerability These types of vulnerabilities are a frequent attack…

Read at CISA advisories

arXiv (research papers) Alexey Kurakin SI

Scaling Adaptive Prompt Injection Attacks with Agent Swarms

Prompt injections have emerged as one of the top security risks faced by AI agents today. Early work in prompt injection attacks looked at simple tool-call agents and static attack payloads, and were saturated since mid-2025. As of Fall 2026, human red-teaming may be nearing saturation, especially on the Gemini family of models. In this work, we argue that despite this apparent plateau, prompt injection attacks are still possible and continued effort into prompt injection…

Read at arXiv (research papers)

arXiv (research papers) Mustafa S. Aljumaily SI

Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models

Tool-using LLM agents act on instructions embedded in the data they read, so prompt injection is a structural rather than a prompt-wording problem. We compare in-prompt defences (hardened prompts, spotlighting, LLM detectors) with deterministic enforcement outside the model (four reference monitors of increasing strength), human approval and taint tracking, judged by one effect-based oracle independent of every defence in an executable environment of 13 tasks and 12 tools…

Read at arXiv (research papers)

Hacker News koeseo SI

Open dataset of prompt-injection CVEs with a monthly threat index

Article URL: https://promptinjections.de/threat-index/zahlen/ Comments URL: https://news.ycombinator.com/item?id=50415821 Points: 3 # Comments: 0

Read at Hacker News

arXiv (research papers) Brijesh Dongol SI

On the Relative Security of Prompt Injection: Mechanised Definitions, Defences and Verdicts for LLM Agents

An LLM agent that reads untrusted content, such as an email or a web page, may follow instructions hidden in it. Noninterference is too strong for such agents, since a useful agent lets untrusted content influence what it does and may disclose the user's data by design, and declassification needs a release policy written for each task. We instead state security relative to a reference agent, which runs the same plan under the same runtime monitor with a model that never…

Read at arXiv (research papers)

arXiv (research papers) Doron Shavit SI

Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation

LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph from the user's objective and the deployment's tool catalog with one LLM call per task, and checks every tool call against it with a deterministic loop that makes no LLM call (median 5.7 microseconds per call). Two further mechanisms recover utility…

Read at arXiv (research papers)

arXiv (research papers) Riya Bharathwaj SI

ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems

As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate across sessions through poisoned shared state, long-context documents, and trusted peer messages: no single message is malicious, yet the assembled tool action is. Prior benchmarks isolate a single agent under prompt injection or score multi-agent attacks by their final output, leaving cross-session erosion of shared state out of…

Read at arXiv (research papers)

Hacker News tclancy SI

Hiding prompt injections in PDFs, and six judges that catch them

Article URL: https://tomclancy.info/joshua-judges-ruth.html Comments URL: https://news.ycombinator.com/item?id=50407255 Points: 1 # Comments: 0

Read at Hacker News

arXiv (research papers) Yichen He SI

CompositionEvidence: Controlling Geometric Evidence for Cinematic Composition Reasoning with Frozen Vision-Language Models

Cinematic composition questions depend on in-frame geometry that vision-language models (VLMs) use inconsistently. External perception tools can expose this geometry, but naive prompt injection can overwrite useful visual predictions. On ShotBench composition, pre-question geometry reduces Qwen2.5-VL-7B from 49.5% to 46.3%; corrupted measurements lower it to 33.6%. CompositionEvidence derives nine reproducible features from frozen detection, depth, and line experts and…

Read at arXiv (research papers)

Hacker News junayedmizan5 SI

Show HN: We tested our prompt injection filter in public

Article URL: https://hodor.gatebolt.com/blog/secret-leak-test Comments URL: https://news.ycombinator.com/item?id=50401639 Points: 1 # Comments: 0

Read at Hacker News

The Guardian Asia-Pacific Oliver Holmes

Eurovision’s Asia experiment gets under way in flamboyant Bangkok

Organisers hope extravagant attempt to transplant song contest will be a success Thailand is about to get a glitz-infused injection of pop culture, with crews starting construction of a large stage in Bangkok as part of an extravagant attempt to transplant Eurovision to Asia. Organisers have promised the world’s longest-running music competition will launch “a new chapter in Asia” next weekend, when 11 contestants from across the region will sing and dance for votes.

Read at The Guardian Asia-Pacific

arXiv (research papers) Mark Heimann SI

Notwithstanding Anything to the Contrary, Ignore All Instructions: Measuring Prompt Injection Guards on Legal Contract Review Attacks

Specialized prompt injection guards are deployed in front of document analysis systems, but no false positive rate has been published for any of them on legal contracts. We measure eleven open-weights guards on two corpora of legal contracts and find that existing guards struggle: document-level false positive rates are as high as 92.39%; two guards fall below chance on paired AUC; and a five-regex baseline is not Pareto-dominated by any guard in the panel. Controlled probes…

Read at arXiv (research papers)

arXiv (research papers) Parth Illendula SI

I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning Agents

Large Reasoning Models (LRMs) are one of the key components of current agentic systems. LRMs augment their output with an explicit chain-of-thought reasoning stage, introducing a new attack surface for thought injection, in which untrusted text resembling the model's own deliberation is fed back to the model. We present a two-part study of this attack, performed against the prevailing large, production class open-weight models (e.g., GLM-5.3, MiniMax-M2.5…

Read at arXiv (research papers)

The Hacker News Security

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artificial intelligence (AI) company in June 2026 as an optional setting to minimize data exfiltration risks arising from prompt injections. "The flaw could enable silent chat data theft, phishing,

Read at The Hacker News

arXiv (research papers) Rongting Zhang SI

Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks

Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent toward an attacker-chosen task. Yet attacker-controlled content can instead tamper with the outcome of the task already in progress. A buyer's dispute evidence can cite a false refund policy to inflate a refund without changing the task. We define IPI by authority rather than instruction-like wording: planted content constitutes an attack when it attempts to…

Read at arXiv (research papers)

arXiv (research papers) Peiran Wang SI

MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark

Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility counterparts, only offering limited task and environment coverage and relying on narrow, static attack scenarios. In this paper, we propose meta-benchmarking for IPI: transforming existing utility benchmarks into end-to-end IPI evaluation suites that…

Read at arXiv (research papers)

arXiv (research papers) Woosang Lim SAINT Machines KAIST SI

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an…

Read at arXiv (research papers)

arXiv (research papers) Woosang Lim SAINT Machines KAIST SI

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an…

Read at arXiv (research papers)

arXiv (research papers) Woosang Lim SAINT Machines KAIST SI

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an…

Read at arXiv (research papers)

arXiv (research papers) Guoqin Xiong SI

SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem. Existing defenses constrain tool calls, trajectories, or information flows, but often leave action semantics, state dependencies, and evidence relations implicit, limiting generalization across heterogeneous tools and complicating safe updates. We present SecureGARD, a dynamic ontology-guided governance…

Read at arXiv (research papers)

SecurityWeek Eduard Kovacs Security

Barracuda ESG Authentication Bypass Flaw Opens Path to Root

An authentication bypass and a command injection flaw can be chained for root access on Barracuda’s Email Security Gateway appliances.

Read at SecurityWeek

arXiv (research papers) Annabella Chow SI

Securing Web Agents with the Compile-Then-Execute Paradigm

Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content. This design makes their control flow vulnerable to prompt injections embedded in webpages. We introduce Baya, a compile-then-execute web agent designed to prevent prompt-injection-driven control-flow hijacking by design. Before accessing the live website, Baya compiles the user's request into an executable Python program that calls…

Read at arXiv (research papers)

arXiv (research papers) Yutao Wu SI

ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud

Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial content, including prompt injections and deceptive interfaces. Beyond such attacks, agents operating on the open web also encounter online fraud designed to deceive humans, including fraudulent online stores, fake investment platforms, and advance-fee schemes. How web agents respond to such fraud during task execution remains…

Read at arXiv (research papers)

arXiv (research papers) Yao Wang SI

Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning

Indirect Prompt Injection (IPI) poses a critical threat to LLM agents. Existing defenses largely focus on whether an injection induces a new tool invocation or unintended action. In this paper, we study a different attack surface, parameter poisoning, where the attacker preserves the intended action but manipulates one or more tool arguments, such as a recipient or other task-critical value. Such attacks are difficult to detect because no new action is introduced, while…

Read at arXiv (research papers)

Older stories