Results for “Agent”
Traders Union: Meta Platforms’ Muse drives investor hopes for new AI agent revenue
“Privacy and data security remain another major hurdle because personal agents rely on deep access to user habits, preferences and private information. Calli Schroeder, senior counsel at the Electronic Privacy Information Center, said the tools create a wide range of risks, including the possibility that agents combine user activity with data purchased from brokers to … Continued
1Password launches a way for AI agents to log in on your behalf without seeing your password
The new feature allows agents to log into a customer's personal accounts while still protecting the private credentials that secure those accounts.
The Foundations of Scalable AI
A scalable AI system requires a strong foundation. Data, engineering, platforms, operating models, and governance must converge to work as one. This session from MIT Technology Review’s EmTech Future conference explores what it takes to build that foundation in a highly regulated environment and how a responsible, trustworthy implementation can turn emerging capabilities, including agentic…
St. Louis Public Radio: With midterms looming, ICE agents investigate suspected voter fraud across Missouri
“Missouri is among nine states listed in a federal lawsuit filed Oct. 15 that were targets of the large-scale investigation by Homeland Security Investigations. The suit filed by the League of Women Voters, Electronic Privacy Information Center and League of United Latin American Citizens alleges DHS illegally collected voting records from at least 47 states … Continued
Chinese hackers spied on thousands of companies after breaching IT giant ConnectWise
Microsoft points the blame for ConnectWise's breach at a China-aligned hacker, which relied on AI agents to rapidly hack into thousands of its customers.
Flint-interactive: A language for creating interactive data visualizations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose.
Uber puts all 30,000 employees on ChatGPT Work
The ride-share giant previously deployed a much smaller pilot for ChatGPT Work but is now taking the enterprise agent company-wide.
Spotify’s current AI bet is about being the music service that agents choose
Spotify co-CEO Gustav Söderström explains why the rise of AI agents could be good news for the music service.
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…
1Password will let AI agents use your passwords without seeing them
As AI agents continue to get more capable, account credentials are becoming more of a hang-up. 1Password is today offering its solution – giving AI agents the ability to use your passwords without actually seeing them, all while leaving you in control.
Anthropic introduces Claude Duet, a proactive AI agent for professionals
Anthropic PBC Wednesday introduced Claude Duet, a proactive artificial intelligence agent for professionals and small business owners in research preview, which completes tasks when asked, keeps working behind the scenes and checks in. Duet is available as a standalone app on the web, iOS and Android for Pro and Max subscribers. The company said the
Startup Action State launches tools for verifying interactions between AI agents
Action State Group Inc. is launching a set of open-source tools designed to let businesses independently check records of what artificial intelligence agents did, addressing a trust problem as automated systems begin buying, selling and delegating work across corporate boundaries. The offering combines EvidenceBook, which preserves tamper-evident records, Terms Packs for evaluating agent behavior and
Your Next Customer Might Be An Agent. Here’s How To Build Your Brand For Both Humans And AI.
As AI agents increasingly recommend and purchase products, brands must appeal to both machines and humans by documenting their voice, creating clear product descriptions and checking how AI summarizes their messaging. Guest author Toby Coulthard suggests that startups should build these practices in from the outset, preserving human appeal while measuring success through conversions and revenue rather than content volume.

Microsoft: Chinese State Actor Used AI to Compromise ConnectWise Tenants
Microsoft said it has observed threat actor activity in multiple ConnectWise customer environments, with the attackers leveraging the ARTEX agentic AI platform
Aegis OS: A Transactional Multi-Tenant Operating System Runtime for Eliminating Authorization Fatigue in Autonomous Coding Agents
Autonomous coding agents such as Google Antigravity (agy), Anthropic Claude Code (claude), and OpenAI Codex CLI (codex) execute multi-step software engineering workflows on workstations and cloud hosts. Existing agent environments face a Security-Autonomy Dilemma: operators must choose between per-action confirmation prompts, which interrupt workflows on 45%-57% of tool calls and induce authorization fatigue, or unconfined execution (--yolo / --dangerously-skip-permissions)…

Symantec Uncovers AI Agent Hijacking Models for Autonomous Cyber-Attacks
Researchers at Symantec have uncovered an AI agent designed to operate a full cyber-attack without human intervention
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…
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…
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…
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…
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…
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
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…
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…
The Window Is in the Reasoning: When LLM Agents Decide to Follow Prompt Injections
LLM agents that read untrusted content can be hijacked by prompt injections. Runtime monitors that try to catch a hijack before the agent acts, and benchmarks that score each task with a single run, share an assumption: whether an agent follows an injection is settled when the injection is read. We test this assumption with branching rollouts that replay an episode exactly up to the step at which the agent reads an injection and then resample the rest of the episode many…
Can the Law Stop AI Hackers?
Hacking law assumes a human intended the break-in. AI agents are testing that assumption, and Congress may need to act.
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal…
Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every failed attack as a successful defense. To test this assumption, we audit 33,000 trajectories from eleven open-weight agents (2-14B parameters) on InjecAgent and AgentDojo. A label-blind LLM judge shows that most failed attacks are…