Language Model Security Database

LLM agents equipped with tool-use, persistent memory, and environmental interaction capabilities are vulnerable to long-horizon attacks. Attackers can bypass single-turn safety guardrails by exploiting the temporal dimension of multi-turn interactions to incrementally steer agent behavior. The vulnerability manifests because the agent's safety mechanisms perform localized, single-step evaluations but fail to maintain semantic safety across extended interaction trajectories. This enables…

Mobile Large Language Model (LLM) agents operating under the "Screen-as-Interface" paradigm are vulnerable to visual indirect prompt injection and state desynchronization. Agents that rely on unstructured visual data (screenshots) and Accessibility Service APIs to perceive the environment lack a mechanism to distinguish between trusted system UI elements and untrusted content (e.g., web pages, emails, or malicious overlays). An attacker can inject visual cues, fake notifications, or hidden…

LLM-based Code Interpreter Agents, including OpenInterpreter and OpenCodeInterpreter, are vulnerable to sandbox evasion and arbitrary code execution via Natural Language Disguise and Contextual Channel Injection. Attackers can bypass Abstract Syntax Tree (AST) static analysis and explicit input guardrails by transforming malicious code logic into descriptive natural language instructions (Code Descriptions), which successfully evade syntax-layer blocks. Additionally, attackers can bypass input…

Conventional LLM agent architectures suffer from a working memory contamination vulnerability due to indiscriminate memory accumulation. When these agents retrieve external data via tools (e.g., web search, reading emails), the entire raw output is appended directly to their continuous context window. If the external data contains an Indirect Prompt Injection (IPI) payload, the malicious instruction persists in the agent's working memory across its entire multi-step reasoning workflow. This…

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…

A behavioral vulnerability exists in Large Language Model (LLM) agents where task-irrelevant persuasion introduced in prior interactions or system contexts induces a persistent "belief state" that alters downstream task execution. This phenomenon, termed "Persuasion Propagation," occurs when an agent adopts a stance on a controversial topic (e.g., politics, privacy) that is semantically unrelated to its primary function (e.g., coding, medical research). This adopted stance acts as a latent…

A vulnerability exists in the similarity-based retrieval mechanisms of long-term memory-augmented Large Language Models (LLMs), specifically affecting systems like Mem0 and A-mem. The vulnerability arises from the system's reliance on dense embedding similarity (e.g., cosine similarity) to retrieve context from dynamic, user-generated memory banks without sufficient semantic validation or conflict resolution. An unprivileged remote attacker can exploit this by injecting "adversarial…

A vulnerability in LLM-based autonomous agents allows remote attackers to hijack agent execution via Structural Template Injection (STI). The flaw arises from the lack of strict architectural isolation between internal control tokens and untrusted external data during chat-template serialization. By embedding framework-specific special tokens (e.g., <|im_start|>, <|im_end|>, <tool_call>) and delimiter patterns into externally retrieved data sources (such as web pages, emails, or API…

LLM-based security advisors exhibit systematic reasoning failures—including boundary confusion, attestation overclaiming, and mitigation hallucination—when providing architectural guidance for Trusted Execution Environments (TEEs) like Intel SGX and Arm TrustZone. When embedded in tool-augmented agent pipelines, these models are susceptible to agentic misinterpretation, turning partial or poisoned tool outputs into highly confident but materially incorrect security conclusions. This…

Tool-calling LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks that induce "Poisoned Chain-of-Thought (CoT)" persistence. When an attacker embeds fake system constraints or error traces into untrusted external content (e.g., tool outputs or retrieved documents), the agent may generate reasoning traces that accept these malicious constraints as ground truth. Even if the original injected input is later sanitized or removed, the residual poisoned reasoning traces remain in the…