Impact

Safety Vulnerabilities

Security concerns affecting AI safety and alignment

61 matching entries out of 781 in this category

Safety research results

61 entries

Agent Lifecycle Compound Threats

Updated 4/10/2026

OpenClaw is vulnerable to persistent memory poisoning, allowing an attacker to manipulate the agent's long-term memory store (MEMORY.md) via prompt injection. Because the autonomous agent continuously integrates this memory file as context for all subsequent reasoning and task planning, injected payloads act as durable behavioral constraints. This allows an attacker to persistently alter the agent's core policy, manipulate tool selection, and hijack future sessions without any further…

Taming openclaw: Security analysis and mitigation of autonomous llm agent threats

Source: arXiv

Arbitrary Agent Topology Breach

Updated 4/10/2026

A vulnerability in LLM-based Multi-Agent Systems (LLM-MAS) allows an attacker who controls a single arbitrary agent to map and extract the system's entire confidential communication topology. Unlike prior attacks that rely on direct identity queries and administrative privileges, this attack infers topology stealthily purely from contextual and linguistic signals (stylometry, role-specific syntax), bypassing standard keyword-based and identity-filtering defenses. The exploit relies on a…

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

Affects: Llama 3 70B, Llama 3.1 8B, Mistral Large 12B +3 more

Source: arXiv

Stage-Sequential Agent Escalation

Updated 4/10/2026

Agentic Large Language Model (LLM) systems utilizing persistent memory, Retrieval-Augmented Generation (RAG) pipelines, and external tool connectors are vulnerable to Logic-layer Prompt Control Injection (LPCI). An attacker can inject obfuscated (e.g., encoded, structurally nested, or semantically reframed) payloads into external memory stores or RAG documents. These payloads bypass conventional inference-time plaintext content filters, persist across session boundaries, and remain dormant…

LAAF: Logic-layer Automated Attack Framework A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems

Affects: GPT-4o Mini, Claude 3 Haiku, Llama 3.1 70B Instruct +2 more

Source: arXiv

Adaptive Web Agent Prompt Injection

Updated 2/21/2026

Large Language Model (LLM) based web agents (such as those built using the BrowserUse scaffold) are vulnerable to Indirect Prompt Injection (IPI) attacks when autonomously navigating and processing untrusted web content. Unlike standard Cross-Site Scripting (XSS), this vulnerability occurs when the LLM orchestrator consumes the DOM or visual screenshots of a webpage containing concealed or contextually disguised adversarial instructions. The LLM interprets these embedded text strings as…

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

Affects: GPT-4.1, GPT-4o, Qwen3-VL 32B Instruct

Source: arXiv

Evolutionary Hidden Knowledge Recovery

Updated 2/21/2026

Large Language Models (LLMs) subjected to machine unlearning techniques (specifically AltPO, GradDiff, IDKDPO, IDKNLL, UNDIAL, NPO, and SimNPO) contain a vulnerability regarding the persistence of latent knowledge. Despite achieving high "forgetting" scores on standard, benign benchmarks, these models remain susceptible to black-box evolutionary adversarial attacks. An attacker can utilize an automated framework (REBEL) comprising a "Hacker" model and a "Judge" model to iteratively mutate…

REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop

Source: arXiv

LLM Backdoor Trigger Reconstruction

Updated 2/22/2026

Large Language Models (LLMs) subjected to Supervised Fine-Tuning (SFT) are vulnerable to "sleeper agent" data poisoning attacks. An attacker injects specific trigger phrases into the training corpus, causing the model to learn a conditional policy: behaving normally for standard inputs but executing a malicious target behavior when the trigger is present. These backdoors persist through safety training and alignment. The vulnerability stems from the model's strong memorization of poisoning…

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Affects: Gemma 3 270M IT, DeepSeek R1 Distill Qwen 1.5B, Phi-4 Mini Instruct +4 more

Source: arXiv

LLM Guardrail Benchmark Lies

Updated 3/8/2026

Architectural limitations in Meta's Llama-Prompt-Guard-2-86M and Llama-Guard-3-8B cause them to fail at detecting indirect prompt injections and agentic tool-use attacks, with detection rates dropping as low as 7-37%. Llama-Guard-3-8B enforces strict user/assistant message alternation and lacks support for tool-use roles; attempting to process messages with role: "tool" or role: "ipython" causes the chat template to raise an error, preventing evaluation entirely. PromptGuard 2 operates…

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

Affects: Llama 3 8B, Llama 3.1 8B

Source: arXiv

Personalized Agent Double Agent

Updated 3/9/2026

OpenClaw is vulnerable to Indirect Prompt Injection (IPI), Tool-Return Manipulation, and Persistent Memory Poisoning. The agent incorporates untrusted external content (e.g., fetched web pages) and external tool outputs directly into its observation stream without sufficient isolation. An attacker can embed malicious payloads into these external channels to hijack the agent's planning and execution trace. This allows the attacker to silently trigger high-privilege actions via OpenClaw's Skills…

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent

Affects: GPT-4o, Llama 3.1 70B, Qwen 2.5 7B

Source: arXiv

Voice Agent Behavioral Bypass

Updated 2/21/2026

Audio Large Language Models (ALLMs) integrated into voice agent systems for high-stakes domains (banking, IT support, logistics) are vulnerable to multimodal adversarial attacks via spoken interaction. Adversaries can exploit the model's inherent compliance and contextual awareness through multi-turn dialogue to bypass authentication safeguards, escalate privileges (e.g., unauthorized credit limit increases), exfiltrate sensitive Personally Identifiable Information (PII), and poison…

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

Affects: GPT-4o, GPT-4o Mini, Gemini 1.5 Pro +4 more

Source: arXiv

Activation-Level Privacy Leak

Updated 2/22/2026

Conversational Large Language Model (LLM) agents integrated with privileged data sources (e.g., medical records, organizational emails) are vulnerable to contextually inappropriate information disclosure due to failures in enforcing Contextual Integrity (CI) norms. Standard semantic input/output filters and generic safety guardrails (e.g., Llama Guard) fail to detect "mosaic attacks" and multi-turn conversational manipulation. In these attacks, adversaries decompose a malicious query into a…

NeuroFilter: Privacy Guardrails for Conversational LLM Agents

Affects: GPT-oss 20B, Llama 3.3 70B Instruct, Qwen 2.5 7B +3 more

Source: arXiv

Related research categories