Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations

operations by 66.2%, detects all 500 tested adversarial storage mutations, and yields zero successful prompt injections across 50 adversarial trials per ATP configuration

Bounded Agents: Delegation Security for Multi-Agent AI Systems

prohibited outcome, or delegate authority to a sub-agent without limiting it. A prompt injection poses a risk only if the agent has authority to perform such actions; this

Rethinking Agent Security as a Networking Problem

driven behavior is inherently nondeterministic and vulnerable to manipulation through attacks such as prompt injection. As a result, current defenses cannot reliably prevent privacy and security threats, highlighting a critical

Stealing Reasoning Traces from Proprietary LLM APIs

safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible

PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents

Smart-home assistants increasingly use multimodal large language models (MLLMs

LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents

LLM-based web agents automate user tasks by observing webpages

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

tools. We show that familiar attack families: poisoning, backdoors, adversarial examples, sensor spoofing, prompt injection, trajectory manipulation, and supply-chain attacks take on distinct meanings when they corrupt world states

@dynatrace-oss/dynatrace-mcp-server's create_dynatrace_notebook missing the human

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces

Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents

creates a distinct authorization problem. Tool-enabled agents can turn model errors and prompt injections into consequential external actions; when evolution occurs under a live grant, the subject exercising that

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

visual understanding activates a weaker refusal tendency than textual understanding. Furthermore, we introduce a prompt injection intervention method that reduces attack success rates by an average of 48.24 percentage points

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

Both trained policies reduce forbidden-content adoption and produce shorter, more focused responses, yet prompt-injection following does not improve. The paired gains are modest and fail to survive Holm

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in Know Your Agent (KYA), a framework that automates black

The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

identify under-recognized risk patterns, including overreliance, uncertainty and legitimacy laundering in retrieval, prompt injection, reward hacking, memory poisoning, evaluation deception, fictional human oversight, synthetic evidence pollution, and model collapse

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models

features concentrate topic-level information in a persistent state. Moreover, as shown in a prompt-injection monitoring case study, slow features preserve detection signals and remain causally effective over long

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored