Prompt injection

Prompt injection and the security of AI models and agents: attacks that hijack chatbots and AI agents through hidden instructions, jailbreaks, data poisoning and the defences against them, from security researchers, arXiv papers, OWASP and the news, plus any story about these attacks.

Summary

109 news articles and 796 research items in this section, back to 20 November 2025. Browse the news ↓ Research ↓

3 stories from 3 publishers in the last 24 hours, 10 from 4 this week.

Most mentioned in Prompt injection headlines, last 3 days: Security 3Prompt 2Injection 2Agent 2

Most active this week: Help Net Security (4), Hacker News (3), The Hacker News (2), SecurityWeek (1). Built automatically from headlines; the top items are the stories the most newsrooms covered in the last three days.

Analysis

Prompt injection has moved from laboratory curiosity to litigated misconduct and a half-billion-dollar acquisition market, as researchers conclude that in-prompt defences cannot be trusted and enforcement must sit outside the model.

The month's most visible episode was a Brazilian court fining lawyers around $16,000 for hiding a prompt injection in a filing, a case that drew unusually heavy discussion and marks the first widely reported judicial sanction for the technique 1819. Commercially, CrowdStrike agreed to pay roughly $495m for Fiddler AI and Dreadnode, and Palo Alto Networks is reported to be negotiating a $500m purchase of Clutch, signalling that incumbents regard agent security as a category worth buying rather than building 141617. Threat reports describe jailbroken or purpose-built agents running autonomous intrusions, including a two-week campaign against a European telecom attributed to a DeepSeek-based agent 726. On the research side, a cluster of papers argues that prompt injection is structural, that human red-teaming is approaching saturation, and that deterministic policy enforcement, intent tracking and taint analysis outside the model are the only defensible path 39404143.

Key developments

  • Brazilian court sanctions lawyers for hidden injection. A Brazilian court fined lawyers roughly $16,000 after the court's own AI flagged hidden text in a filing demanding superficial legal scrutiny, according to the linked reports [18][19]. The story reached 348 points and 220 comments on Hacker News, far more than any other item in the period, indicating broad public recognition that prompt injection is now a legal and ethical issue, not merely a technical one [19]. It sits alongside a separate write-up on using 'lawyerspeak' to bypass agent guardrails, suggesting legal register is both a weapon and a venue [3]. 18193
  • Incumbents buy into agent security at scale. CrowdStrike said it will acquire Fiddler AI (agent observability) and Dreadnode (automated AI security testing) for a reported combined $495m, adding both to its Falcon platform [16][17]. TechCrunch separately reports Palo Alto Networks in talks to buy Clutch for about $500m, a company last valued at $85m according to a single source, so that figure should be treated as unconfirmed [14]. Obsidian Security's new Runtime Policy Decision Engine, which vets agent actions before execution, and OpenAI's engagement of startup Hacktron for testing show the same demand from both vendors and model labs [4][13]. 141617413
  • Autonomous and jailbroken agents attacking real targets. Malbear Labs reported that a jailbroken DeepSeek agent spent two weeks attacking a European telecom, and Symantec separately uncovered an agent designed to run a full cyber-attack without human intervention [7][26]. Check Point disclosed 'Haiou', a Codex jailbreak bundle that rewrites an agent's trusted instructions to inject adverts for a third-party AI gateway, a phenomenon it calls prompt adware [15]. Researchers are responding with 'shibboleth traps', honeypots designed to fingerprint the model and harness behind an agentic attack from telemetry [37]. 7261537
  • Research consensus: treat the model as untrusted. Several papers converge on deterministic enforcement outside the model: reference monitors with taint tracking and human approval [40], mechanised noninterference-style definitions with release policies [41], intent graphs auditing tool calls for least privilege [43], and intent-aware protection that asks whether an agent remains faithful to its deployed purpose [33]. CapLite questions whether small-model agents can even be trusted to write the security artefacts that schemes such as CaMeL and Progent rely on [31]. This matches Obsidian's commercial pre-execution policy approach [4]. 4041433331
  • Attacks scale while red-teaming saturates. One paper states that static payload attacks were saturated by mid-2025 and that human red-teaming may be nearing saturation in autumn 2026, proposing adaptive agent swarms to keep pressure on defences [39]. Others show that resizing or re-rendering an image can reveal instructions invisible at one resolution [32], that benign requests can escalate into unsafe actions across multi-agent sessions via poisoned shared state [44], and that the execution harness, not just the backend model, determines web-agent resilience [38]. Together these widen the attack surface beyond text and beyond any single model. 39324438
  • Injection risk crosses into the physical world. DeepMind released Gemini Robotics 2.5 together with an open safety benchmark named ASIMOV-jailbreak [5], while a separate paper examines coding agents that control real robot arms zero-shot and the safety risks that arise at the digital-physical boundary [42]. The combination means a successful injection could translate into physical action rather than a leaked secret, raising the stakes for the enforcement work above. 542

Themes

  • Detection products proliferate, traction is thin. A steady stream of Show HN posts offers filters, judges and token-level gates, including formal-logic detectors, PDF injection judges, positional scanners and 'System 1' decision models, yet almost all registered one to three points and no comments [2][11][12][20][25][28][29][30]. The contrast with the heavily cited enforcement research and nine-figure acquisitions suggests the market is moving past phrase-matching toward runtime control and observability [40][16]. 211122025
  • Governance and workforce catching up. ISC2 launched a vendor-neutral Cyber-AI Workforce Coalition and is recruiting 3,000 volunteers for a pilot of its first AI security certification, expected in early 2027 [21][22]. An IANS report finds head-of-AI-security roles surging in large organisations while accountability for AI governance remains unsettled, echoing a gateway governance write-up asking 'who governs the governor' [27][23]. 212227238
  • Supply chain and tooling as attack vectors. Prompt adware hidden in a jailbreak toolkit, stored injections through API gateways and new research on AI supply-chain exposure all point to compromise upstream of the deployed agent [15][23][6]. Open datasets of prompt-injection CVEs with a monthly threat index indicate the community is beginning to track these as conventional vulnerabilities [10]. 1523610

What to watch

  • Whether Palo Alto Networks confirms the reported $500m Clutch acquisition, which would make two near-identical bets by major incumbents within a week and validate the agent-security category [14][16][17]. 141617
  • Further court or regulatory sanctions following the Brazilian case, which would establish prompt injection as recognised professional misconduct beyond one jurisdiction [18][19]. 1819
  • Independent validation of the telecom and Symantec agent-attack reports and adoption of fingerprinting techniques, since both are single-source findings so far [7][26][37]. 72637
  • Take-up of the ASIMOV-jailbreak benchmark and the ISC2 certification pilot as indicators of whether safety evaluation and skills are being standardised rather than left to vendors [5][22]. 522
Stories this analysis is based on (35)
  1. Show HN: Deterministic prompt injection detector using formal logic Hacker News
  2. Prompt Injection, Esq.: pwning AI agent guardrails with lawyerspeak Hacker News
  3. Obsidian expands AI agent security with runtime policy enforcement Help Net Security
  4. DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak" Ars Technica
  5. How AI security failures are endangering your supply chain – and what you can do ZDNET AI
  6. Jailbroken AI Agent Ran Two-Week Attack on European Telecom Infosecurity Magazine
  7. AI Security Schneier on Security
  8. Open dataset of prompt-injection CVEs with a monthly threat index Hacker News
  9. Hiding prompt injections in PDFs, and six judges that catch them Hacker News
  10. Show HN: We tested our prompt injection filter in public Hacker News
  11. OpenAI taps AI security startup Hacktron to test systems Tech in Asia
  12. Palo Alto Networks in talks to buy AI agent security startup Clutch for $500M TechCrunch
  13. Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit The Hacker News
  14. CrowdStrike to shell out nearly $500M for 2 AI security startups as the market for securing agents takes off TechCrunch
  15. CrowdStrike Reportedly Paying $495 Million for AI Security Firms Fiddler, Dreadnode SecurityWeek
  16. Brazilian lawyers fined $16K for hiding a prompt injection in a court filing Hacker News
  17. Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing Hacker News
  18. Blazle – Block prompt injection and secret leaks before AI agents act Hacker News
  19. ISC2 Launches Cyber-AI Workforce Coalition to Address the Future of AI Security Jobs Infosecurity Magazine
  20. First ISC2 AI Security Certification Expected for Early 2027 Infosecurity Magazine
  21. Who Governs the Governor? – Stored Prompt Injection Through the API Gateway Hacker News
  22. Prompt injection scanners should be positional, not phrasal Hacker News
  23. Symantec Uncovers AI Agent Hijacking Models for Autonomous Cyber-Attacks Infosecurity Magazine
  24. Head of AI Security Roles Surge in Large Organizations Infosecurity Magazine
  25. CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts arXiv (research papers)
  26. Scale-Induced Semantic Shift in Visual Prompt Injection Against VLMs and Web Agents arXiv (research papers)
  27. Intent-Aware Protection for AI Agents arXiv (research papers)
  28. Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks arXiv (research papers)
  29. Harness Matters: Measuring and Dissecting Security Resilience in Web Agents arXiv (research papers)
  30. Scaling Adaptive Prompt Injection Attacks with Agent Swarms arXiv (research papers)
  31. 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 arXiv (research papers)
  32. On the Relative Security of Prompt Injection: Mechanised Definitions, Defences and Verdicts for LLM Agents arXiv (research papers)
  33. When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary arXiv (research papers)
  34. Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation arXiv (research papers)
  35. ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems arXiv (research papers)

Written by Claude Fable 5.1 (Anthropic), based on 45 recent headlines and excerpts in this section, 3d ago. AI analysis can misread or miss things: the numbers link to the original reporting, which is the authority.

Research 796

Journal articles, academic blogs, think-tank reports and papers, kept apart from the news below.

arXiv (research papers) Dohyeon Kwon SI

SEOYUN: Refusal-Inducing Exam Documents for AI-Glasses Pipelines

Camera-equipped glasses can convert an examination page into a query to a vision-language model (VLM). Device detection addresses possession; a complementary question is whether an examination document can reduce the usefulness of an unauthorized capture. We present SEOYUN, an application-specific framework for refusal-inducing exam documents, with optical and encoder-level interventions as extensions. We use reverse jailbreaking to describe the direction of the objective…

Read at arXiv (research papers)

arXiv (research papers) Lipeng He Security

PIPETTE: Prompt Injection Purple-Teaming for Robust LLM Agents

Large language model (LLM) agents routinely interact with untrusted external data, exposing them to indirect prompt injection (IPI) attacks that hijack agents into executing attacker-chosen tasks. To uncover these vulnerabilities at scale, automated red-teaming methods often leverage reinforcement learning (RL) to generate attacks that achieve high attack success rates (ASR). Model developers use the attacks discovered during internal red-teaming to harden agents through…

Read at arXiv (research papers)

arXiv (research papers) Stavros Damianakis Security

AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents

Prompt injection is the dominant unsolved security risk for LLM agents, and the community now agrees that robustness must be measured against adaptive attackers rather than fixed benchmark injections. Many adaptive red teamers exist, and most are built to maximize attack success rate (ASR). Yet ASR counts how often a target breaks, not in how many different ways. A red teamer can achieve a high ASR by reusing a few techniques that work, leaving the others untested and absent…

Read at arXiv (research papers)

arXiv (research papers) Haoyang Liu Security

What Survives the Shift from Text to Pixels? Conditional Protection against Prompt Injection in Image-Rendered Documents

Multimodal language models increasingly answer questions over external documents, exposing them to indirect prompt injection: commands planted in untrusted content to hijack the response. Rendering untrusted content as page images lowers attack success on average, leaving open which injected operations survive rendering, at what utility cost, and whether failed image attacks reflect unread commands or commands read but not followed. We pair text and page-image versions of…

Read at arXiv (research papers)

arXiv (research papers) Bonan Ruan Security

Guarding the Kingdom of Skill-Based Agents in the AI Dynasty of Computation: Control-Flow Integrity for Agent Skills

Control-flow integrity (CFI) confines a program to a control-flow graph fixed ahead of time. Procedural agent skills move this control flow into prompt text, and a large language model (LLM) agent decides at runtime whether each step runs in its reasoning, a tool call, or a script. The procedure's control skeleton survives, but its enforceability depends on where each step runs. Many violations, such as overwriting a file before validation, use only operations the skill…

Read at arXiv (research papers)

arXiv (research papers) Tingxuan Han Security

Data Poisoning Attacks to Locally Differentially Private Triangle Counting Protocols

Local differential privacy (LDP) has become a crucial paradigm for privacy-preserving graph analytics, enabling graph analytics tasks such as subgraph counting without requiring a trusted curator. However, while LDP provides strong privacy guarantees, the integrity and robustness of LDP subgraph counting protocols in the presence of malicious participants remain poorly understood. In particular, since data are randomized locally before collection, it is inherently difficult…

Read at arXiv (research papers)

All 796 research items in this section

All news 109

Help Net Security Mirko Zorz Security

Your AI red team may be finding the same prompt injection thousands of times

AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working attacks produced the weaker defense. Prompt injection purple-teaming workflow (Source: Research paper) Someone hides instructions in an email, a web page or a tool’s output, and the AI agent that ……

Read at Help Net Security

Hacker News StackBuilders SI

AI Agent Authorization That Limits the Damage of Prompt Injection

Article URL: https://www.stackbuilders.com/insights/ai-agent-authorization-that-limits-the-damage-of-prompt-injection/ Comments URL: https://news.ycombinator.com/item?id=50566999 Points: 2 # Comments: 0

Read at Hacker News

The Hacker News Security

ThreatsDay: GPT-6.2 Jailbreak Flaws, BubbleLoader PNG Malware, $500M Ransom Demands + 17 More Stories

The easiest way to fool someone is to give them something they already expect. A job offer. A message about a service outage. A familiar app. Nothing looks strange at first. And that's the problem. This week's stories show how ordinary things are being used to steal data, spread malware, and get people to hand over access. There's another shift worth watching. AI is making some attacks easier

Read at The Hacker News

SecurityWeek Kevin Townsend Security

VeroSecurity Raises $11 Million for AI Security Engineering Platform

AI Security Engineering is a new and essential security discipline now being brought into focus by VeroSecurity.

Read at SecurityWeek

Help Net Security Mirko Zorz Security

Ubuntu AI security patches are here, if you’re willing to test them yourself

Canonical is letting Ubuntu Pro customers install security patches written by AI agents before its engineers finish reviewing and testing them. The patches come from Surge, a system Canonical built to fix known vulnerabilities in Ubuntu’s userspace software, meaning everything outside the operating system’s kernel. They ship through a new opt-in channel called the Edge archive. If you leave Edge switched off, nothing changes in how your updates are checked: Ubuntu’s regular…

Read at Help Net Security

The Hacker News Security

Apple Tightens macOS App Permissions to Limit Data Access Amid AI Agent Security Risks

Apple on Monday introduced new controls that allow Mac users to give more granular access to data they give to apps, including those that use artificial intelligence (AI) agents. The changes, currently previewed in macOS 27.3 beta 2, relate to increased transparency and more options for two of its APIs: Device Control and Data Access, and Full Disk Access. "Before granting an app such

Read at The Hacker News

Help Net Security Mirko Zorz Security

Too many instructions can hold back AI security audits

In this Help Net Security interview, Peter Stöckli, Security Researcher at GitHub, explains how the team uses AI agents to audit software for vulnerabilities. The discussion covers why the work started with authentication and authorization bugs, how prompts are tested and trimmed for each model, and what the agent produces during threat modeling. Stöckli also describes how every report is checked by a person before it reaches maintainers, how false positives are filtered…

Read at Help Net Security

Help Net Security Mirko Zorz Security

AI security took more than one in three cybersecurity seed funding deals

Seed deals for cybersecurity startups dipped slightly in the third quarter of 2026, the second decline in a row, while the wider U.S. venture market had one of its best quarters since 2021. Investment firm DataTribe tracked the split using PitchBook data on U.S. seed through Series E rounds, and sorted the cyber seed deals into categories. Across the market, capital is pooling in fewer, larger rounds, and the bar for the round after seed … More →

Read at Help Net Security

Hacker News iqra_c SI

Prompt Injection Attacks in Large Language Model Systems

Article URL: https://zenodo.org/records/21357273 Comments URL: https://news.ycombinator.com/item?id=50507246 Points: 2 # Comments: 1

Read at Hacker News

Hacker News nischoy SI

Show HN: Deterministic prompt injection detector using formal logic

This is a prompt-injection detector I built using NLP and SMT2. Comments URL: https://news.ycombinator.com/item?id=50501132 Points: 1 # Comments: 0

Read at Hacker News

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

Help Net Security Industry News Security

Obsidian expands AI agent security with runtime policy enforcement

Obsidian Security has announced its Runtime Policy Decision Engine, giving security teams centralized control over AI agent actions before they run. Building on Obsidian’s extensive AI agent discovery and governance coverage, the engine uses context about who is behind an agent, its access and the third-party applications involved to allow or block actions, or require human approval where supported. Context from your apps, identity systems and your own labels feeds one…

Read at Help Net Security

Ars Technica Ryan Whitwam SI

DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"

The new model is up to twice as successful at some tasks.

Read at Ars Technica

ZDNET AI Charlie Osborne SI

How AI security failures are endangering your supply chain – and what you can do

New research provides a stark look at the AI supply chain and the risks it brings to businesses.

Read at ZDNET AI

Infosecurity Magazine Security

Jailbroken AI Agent Ran Two-Week Attack on European Telecom

Jailbroken DeepSeek agent spent two weeks attacking a European telecom, Malbear Labs found

Read at Infosecurity Magazine

Schneier on Security Bruce Schneier Security

AI Security

Two weeks ago, I attended the [un]prompted AI security conference in San Francisco. It was an excellent event: three days of very dense talks about all aspects of AI security. (My talk was about integrous AI, and I will post it when it is online.) AI security can be divided into three broad topics. It’s important for researchers to understand which one they are working on. And it’s important for us as a community to work on them all. They are: security of AI, security with…

Read at Schneier on Security

MarkTechPost Michal Sutter SI

0sec Labs Open-Sources 0, an AI Security Harness With Web UI, CLI and MCP

0sec Labs has open-sourced 0, an AI security harness for code review, pentesting, reverse engineering and fixes. It runs locally through a browser console, a headless CLI and an MCP server, with your own model provider.

Read at MarkTechPost

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

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

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

Tech in Asia Minh Le Startups

OpenAI taps AI security startup Hacktron to test systems

Hacktron previously raised US$2.9 million to build an AI-powered security testing platform.

Read at Tech in Asia

TechCrunch Marina Temkin SI

Palo Alto Networks in talks to buy AI agent security startup Clutch for $500M

Clutch, backed by Lightspeed and SignalFire, was last valued at $85 million, according to a source.

Read at TechCrunch

The Hacker News Security

Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit

Cybersecurity researchers have disclosed details of an OpenAI Codex jailbreak bundle that's designed to modify an artificial intelligence (AI) agent's trusted instructions to insert advertisements for a third-party AI gateway. The phenomenon has been codenamed prompt adware by Check Point Research. Called Haiou (meaning Seagull in Chinese), the jailbreak modifies OpenAI Codex's configuration

Read at The Hacker News

TechCrunch Ram Iyer SI

CrowdStrike to shell out nearly $500M for 2 AI security startups as the market for securing agents takes off

CrowdStrike said it will buy Fiddler AI, which makes AI agent observability software, and Dreadnode, which helps companies automate AI security testing.

Read at TechCrunch

SecurityWeek Eduard Kovacs Security

CrowdStrike Reportedly Paying $495 Million for AI Security Firms Fiddler, Dreadnode

The acquisitions will add AI agent observability and automated AI security testing capabilities to the CrowdStrike Falcon platform.

Read at SecurityWeek

Hacker News entryleveljobsc SI

Brazilian lawyers fined $16K for hiding a prompt injection in a court filing

Article URL: https://www.tomshardware.com/tech-industry/artificial-intelligence/brazilian-lawyers-busted-for-attempting-to-manipulate-courts-ai-with-prompt-injection-hidden-in-filing-courts-ai-flags-hidden-text-that-demanded-superficial-legal-scrutiny-lawyers-fined-usd16-000 Comments URL: https://news.ycombinator.com/item?id=50326514 Points: 1 # Comments: 2

Read at Hacker News

Hacker News doodlesdev SI

Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing

Article URL: https://jetstream.security/insights/brazilian-court-sanctions-prompt-injection-filing/ Comments URL: https://news.ycombinator.com/item?id=50322173 Points: 348 # Comments: 220

Read at Hacker News

Hacker News ricky_anh_nguye SI

Blazle – Block prompt injection and secret leaks before AI agents act

Article URL: https://www.blazle.io/ Comments URL: https://news.ycombinator.com/item?id=50263366 Points: 1 # Comments: 0

Read at Hacker News

Infosecurity Magazine Security

ISC2 Launches Cyber-AI Workforce Coalition to Address the Future of AI Security Jobs

ISC2’s new Cyber-AI Workforce Coalition serves as a “vendor-neutral convener” to map the future of AI security careers, ISC2 CEO Scott Beale told Infosecurity

Read at Infosecurity Magazine

Infosecurity Magazine Security

First ISC2 AI Security Certification Expected for Early 2027

ISC2 is seeking 3000 volunteers to enrol to a pilot exam phase for its upcoming AI security certification

Read at Infosecurity Magazine

Older stories