Results for “Injection”

arXiv (research papers) Mostafijur Rahman Akhond SI

Then there is prompt injection, a malicious email, ...: The Wild Wide West of OpenClaw Agentic System Security

AI-powered personal assistant frameworks such as OpenClaw combine LLM reasoning, persistent memory, tool invocation, local execution, and web-based workflows. These capabilities enable useful automation, but they also create security risks when untrusted inputs, model reasoning, tools, memory, and deployment configuration interact without explicit trust boundaries. This paper presents an empirical study of reported security concerns in OpenClaw using two complementary data…

Read at arXiv (research papers)

arXiv (research papers) Weihang Niu SI

Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition

This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pipelines. In the IJCAI 2026 OpenClaw Agent Security Attack Competition, each attack package is judged by a static skill scan (S1), an LLM-judge safety check over the task and skill definition (S2), and a live execution audit (S3). Our observations suggest a scope gap: S2 appears to inspect the task instruction and skill definition without inspecting…

Read at arXiv (research papers)

arXiv (research papers) Md Abu Yusuf SI

SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments

Large language model (LLM) agents are increasingly wired to consequential tools that send public alerts, dispatch responders, and query citizen records, where one erroneous tool call carries real-world cost. Existing agent-safety benchmarks measure generic harm or prompt-injection success and implicitly treat refusing as the safe default. In public-safety deployments that assumption breaks: an agent too cautious to dispatch help fails as surely as one that triggers a false…

Read at arXiv (research papers)

Hacker News auraham SI

Prompt Injection Techniques Every Red Teamer Should Test

Article URL: https://fdzdev.medium.com/20-prompt-injection-techniques-every-red-teamer-should-test-b22359bfd57d Comments URL: https://news.ycombinator.com/item?id=50228983 Points: 2 # Comments: 0

Read at Hacker News

Hacker News vnutrivas SI

Prompt injection scanners should be positional, not phrasal

Article URL: https://attest.rta.lat/article Comments URL: https://news.ycombinator.com/item?id=50223560 Points: 2 # Comments: 0

Read at Hacker News

arXiv (research papers) İpek Abasıkeleş Turgut SI

Deletion, Substitution, Repair and Transplant: Component Attribution in BARBICAN, a Layered Prompt-Injection Gateway for MCP

A neural classifier can fail completely inside a layered defense without any end-to-end number moving. We demonstrate this on BARBICAN, a fail-closed gateway for language-model tool mediation whose arbitration stage spent an entire recorded evaluation receiving text mangled by a misconfigured tokenizer. Correcting the misconfiguration lifts that stage's corpus-wide area under the ROC curve (AUC) from 0.392 to 0.855 and pushes system recall down, from 80.67% to 80.34%; a stub…

Read at arXiv (research papers)

arXiv (research papers) Yuyang Gong SI

On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection

Prompt injection benchmarks assess whether large language models (LLMs) and agents resist malicious instructions embedded in external content. However, a system could perform well by rejecting attacks that obviously abandon the user's request, while still accepting changes that retain most of a legitimate answer but make it incorrect or harmful. Testing more instructions for unrelated outcomes would not necessarily reveal this weakness. We call attacks seeking responses…

Read at arXiv (research papers)

CISA advisories CISA Security

CISA Adds One Known Exploited Vulnerability to Catalog

CISA has added one new vulnerability to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-114625 Arista VeloCloud Orchestrator SQL Injection Vulnerability This type of vulnerability is a frequent attack vector for malicious cyber actors and poses significant risks to the federal enterprise. Binding Operational Directive (BOD) 26-04: Prioritizing Security Updates Based on Risk establishes vulnerability management…

Read at CISA advisories

CISA advisories CISA Security

CISA Adds One Known Exploited Vulnerability to Catalog

CISA has added one new vulnerability to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-110447 Collabora Online – Built-in CODE Server OS Command Injection Vulnerability This type of vulnerability is a frequent attack vector for malicious cyber actors and poses significant risks to the federal enterprise. Binding Operational Directive (BOD) 26-04: Prioritizing Security Updates Based on Risk establishes vulnerability…

Read at CISA advisories

arXiv (research papers) Eric Yocam SI

Agentic AI Defense: Decode-Time Provenance Binding for MCP

Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, in which instructions concealed in an email-signature image using least-significant-bit (LSB), discrete cosine transform (DCT), or metadata steganography bypass text scanners and enter a multi-agent workflow when decoded by a tool. To counter this threat, we propose decode-time provenance binding…

Read at arXiv (research papers)

arXiv (research papers) Chao Gu SI

Certified Execution Harness for Agentic AI: Safe and Least-Intrusive Petri-Net Supervisory Control Between Reasoning and Action

This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize the execution harness between the LLM and its tools as a supervisory control problem, in which marks represent capabilities, approvals and budgets. Since a transition fires only if the marks it needs are present, an injected request whose preconditions are unmet or already spent is refused regardless of its wording. Treating tool…

Read at arXiv (research papers)

Journal articles (OpenAlex) Amanda M. Ferrante, Basia M. Michalski-McNeely · Dermatologic Surgery Geopolitics

Botulinum Toxin and Dermal Filler: Discordant Legislation, Regulations, and Guidelines in the United States

BACKGROUND: Botulinum toxin and dermal filler injections are the most commonly performed minimally invasive cosmetic procedures in the United States. These injectables require extensive medical training, experience, and oversight to be administered safely due to risk of significant complications. However, rules and regulations governing their administration differ widely across states. OBJECTIVE: To summarize the legal statutes, regulations, codes, and professional…

Read at Journal articles (OpenAlex)

arXiv (research papers) Frank Breitinger SI

Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations

Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital forensics inverts the usual setting for indirect prompt injection: the evidence under analysis is attacker-controlled by definition, and the examiner is obliged to read it closely. This makes the reasoning layer a new anti-forensic target, next to the classical ones of data and tools. Classical anti-forensic taxonomies do not cover it, and prompt injection…

Read at arXiv (research papers)

arXiv (research papers) Yiheng Li SI

MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning

With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narratives or visual inputs to bypass safety alignment. Existing approaches, such as signature- and perplexity-based methods, rely heavily on pattern matching, making them insufficient to detect sophisticated, cross-modal PI payloads. In this paper, we…

Read at arXiv (research papers)

arXiv (research papers) Peiyang Liu SI

Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint

Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection. Yet RAG protection studies use incompatible evaluation metrics, datasets, and threat models. We present a systematic survey and human-coded evidence map of 118 full-text-confirmed RAG defense papers, organized by measured endpoint rather than claimed goal or defense mechanism. Our…

Read at arXiv (research papers)

arXiv (research papers) Amelia Kawasaki SI

Attention-based Classification for Indirect Prompt Injection

Indirect prompt injection (IPI) attacks, in which adversarial instructions are embedded in external data processed by a language model, pose a significant threat to the integrity of deployed LLM agents. Attention Tracker (Hung et al., 2025) is a recently proposed white-box detection method that identifies prompt injection attacks by monitoring how a model's attention is distributed between user task tokens and data tokens, claiming dataset-agnostic detection via a scalar…

Read at arXiv (research papers)

arXiv (research papers) Pedro H. Barcha Correia SI

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to bypass intended behavior and operational boundaries. In traditional chatbots, such attacks are confined to a single session because state memory is not preserved across conversations. However, persistent memory features in modern conversational…

Read at arXiv (research papers)

arXiv (research papers) Zhiyue Xu SI

After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent without user input. A one-time indirect prompt injection committed to either channel can re-fire across sessions long after the attacker leaves, threats we term carryover attacks. Existing prompt-injection benchmarks evaluate attacks only in the session where malicious content is first observed, leaving the…

Read at arXiv (research papers)

arXiv (research papers) Abhishek Rai SI

Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG

Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-parameter small language model that acts as a semantic firewall between retrieval and generation. It jointly evaluates the user query and retrieved context, classifying the pair as safe, suspicious, or malicious. The model is trained…

Read at arXiv (research papers)

Hacker News denn-gubsky SI

Decision model as prompt-injection judge: 40 of 40 on 78 texts

Article URL: https://loomcycle.dev/blog/decision-model-as-prompt-injection-judge Comments URL: https://news.ycombinator.com/item?id=50166532 Points: 1 # Comments: 0

Read at Hacker News

Hacker News Hiskias SI

Building a System One Model for Prompt Injection

Article URL: https://www.stackone.com/blog/system-one-model-prompt-injection/ Comments URL: https://news.ycombinator.com/item?id=50165645 Points: 2 # Comments: 0

Read at Hacker News

Hacker News regsiren SI

Show HN: SentinelGate – Drop prompt injections at Token 0 before LLM inference

Article URL: https://sentinelgate.dev Comments URL: https://news.ycombinator.com/item?id=50165432 Points: 1 # Comments: 0

Read at Hacker News

arXiv (research papers) Mengxiao Wang SI

Fake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents

Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricated headlines from real news. Because they read the same feeds under near-identical policies, a single fabricated post can push them into the same trade at the same moment. We present a systematic attack benchmark for information injection against LLM trading agents. Unlike prompt injection, which targets the model's instructions, information injection…

Read at arXiv (research papers)

arXiv (research papers) Yinxiang Wang SI

SpanGuard: Decoupling Instruction Localization from Authorization for Lightweight IPI Defense

LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the guardrail model becomes smaller or weaker, detection degrades substantially. This raises a natural question: can we retain strong IPI defense while relying only on a small LLM? To understand why, we revisit what an LLM guardrail actually does. Detecting IPI requires simultaneously locating potentially injected instructions within…

Read at arXiv (research papers)

arXiv (research papers) Yuchen Chen SI

RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external knowledge bases also introduces new attack surfaces. Existing data extraction attacks against RAG systems rely on either prompt injection, which heavily depends on the generator's instruction-following capability, or backdoors that reproduce or paraphrase retrieved documents but struggle to balance extraction fidelity and…

Read at arXiv (research papers)

Hacker News joebig SI

LLM01: 2025 Prompt Injection

Article URL: https://genai.owasp.org/llmrisk/llm01-prompt-injection/ Comments URL: https://news.ycombinator.com/item?id=50144431 Points: 1 # Comments: 0

Read at Hacker News

arXiv (research papers) Stavros Damianakis SI

SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space

Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed. More than twenty public datasets describe prompt injection using incompatible vocabularies, often organized around delivery vector, attacker goal, or generation method. In this Systematization of Knowledge, we present PIAtlas, a taxonomy organized instead around how the injected instruction is…

Read at arXiv (research papers)

Hacker News adikshatriyag SI

Show HN: AegisKernel – Test prompt injection attacks on AI agents in the browser

Article URL: https://adikshatriyag-crypto.github.io/aegis-kernel/ Comments URL: https://news.ycombinator.com/item?id=50132623 Points: 1 # Comments: 0

Read at Hacker News

arXiv (research papers) Yuntao Du SI

RATION: Towards Quantitative Risk-Based Access Control for AI Agents

AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead to unexpected behavior and expose agents to security threats such as indirect prompt injection. Current agent security systems largely protect agents by restricting their actions, which can result in a substantial security-utility trade-off for complex, open-ended tasks. To address this, we propose a quantitative risk-based approach to access control for AI…

Read at arXiv (research papers)

arXiv (research papers) Egor Zverev SI

SPIDES: Information-Flow Control for Browser Agents

Browser agents automate complex workflows by reading and acting on arbitrary page content, but this flexibility exposes them to prompt injection attacks and unintended data exfiltration. Recent work argues that LLM-driven browser agents erode traditional web security boundaries such as the Same-Origin Policy (SOP) by acting across origins with the user's authority and no built-in isolation. We argue that restoring SOP is neither sufficient (a same-origin public sink can leak…

Read at arXiv (research papers)

Older stories