LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

OWASP-based analysis reveals recurring architectural risk patterns, especially Supply Chain, Excessive Agency, and Prompt Injection, which often co-occur across multiple stages of execution. These results suggest that existing

Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem

taxonomy of risks in the MCP ecosystem, distinguishing between adversarial security threats (e.g., indirect prompt injection, tool poisoning) and epistemic safety hazards (e.g., alignment failures in distributed tool delegation

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

handling. MSB contributes: (1) a taxonomy of 12 attacks including name-collision, preference manipulation, prompt injections embedded in tool descriptions, out-of-scope parameter requests, user-impersonating responses, false-error

CALYREX: Cross-Attention LaYeR EXtended Transformers for System Prompt Anchoring

untrusted user content with equal structural priority -- a mismatch that leaves models vulnerable to prompt injection and instruction erosion over extended contexts. We propose CALYREX (Cross-Attention LaYeR EXtended transformers

Ranked but Not Stopped: Detecting Prompt-Injection Hijacks from Typed Decision Models' Output Probabilities

Programs that use a language model as a classifier act

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments

Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges

taxonomy of attack vectors, covering topics such as jailbreaking, backdoor attacks, and multi-modal prompt injection. In response, we analyze and categorize a range of defense mechanisms, from formal safety

Sentra-Guard: A Multilingual Human-AI Framework for Real-Time Defense Against Adversarial LLM Jailbreaks

time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with FAISS

OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence

OpenSec, a dual-control reinforcement learning (RL) environment that evaluates IR agents under realistic prompt injection scenarios with execution-based scoring: time-to-first-containment (TTFC), evidence-gated action rate

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval

implanting malicious successful experiences into the agent's long-term memory. Unlike traditional prompt injections that are transient, or standard RAG poisoning that targets factual knowledge, MemoryGraft exploits the agent

Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents

integrated with a human-in-the-loop review process. Evaluations show our system reduces prompt-injection risk, blocks out-of-scope requests, and limits toxic outputs. It also generates auditable

The Shawshank Redemption of Embodied AI: Understanding and Benchmarking Indirect Environmental Jailbreaks

prompts to the embodied agent. In this paper, we propose, for the first time, indirect environmental jailbreak (IEJ), a novel attack to jailbreak embodied AI via indirect prompt injected into

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Thinking, and Phi-4, and across out-of-distribution benchmarks spanning harmful tasks, prompt injection, benign tool use, and cross-domain privacy leakage. MOSAIC reduces harmful behavior

API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary

prompt or tool configuration, crosses from an authentication boundary into a data pipeline, where it may persist in conversation history, logs, memory stores, generated code, and error payloads. Prompt injection

Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching

should handle a user request. Existing attacks on this stage primarily rely on explicit prompt injection or instruction-level steering, which can expose recognizable manipulation signals. In this work

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents

process untrusted content, maintain memory, delegate across agents, and invoke side-effecting tools. Existing prompt-injection evaluations typically summarize security with terminal attack or policy outcomes, but equal endpoints

Practical and Stealthy Touch-Guided Jailbreak Attacks on Deployed Mobile Vision-Language Agents

safety alignment of LVLMs. Moreover, we developed three representative Android applications and curated a prompt-injection dataset for mobile agents. We evaluated our attack across multiple LVLM backends, including closed

OpenClaw: Lower-trust background runtime output is injected into trusted

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

training-free framework for multi-event video generation. Our key insight is that uniform prompt injection across time ignores the correspondence between events and frames. To this end, we introduce

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

training-free framework for multi-event video generation. Our key insight is that uniform prompt injection across time ignores the correspondence between events and frames. To this end, we introduce