Language Model Security Database

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…

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…

Agentic LLM systems that automatically preview URLs or extract web metadata are vulnerable to implicit prompt injection, resulting in silent data exfiltration ("silent egress"). Attackers can embed adversarial instructions in unobserved web elements, such as HTML <title> tags, <meta> descriptions, or Open Graph metadata. When a user requests a summary of the URL—or when the agent automatically unfurls a linked URL in a chat—the system fetches the malicious page and flattens this metadata into…

Self-evolving Large Language Model (LLM) agents that utilize long-term memory mechanisms (such as Vector Databases for Retrieval-Augmented Generation or Sliding Window buffers) are vulnerable to persistent indirect prompt injection. This vulnerability, termed "Zombie Agent," occurs when the agent's memory update function ($F_M$) processes attacker-controlled content retrieved from external sources (e.g., web pages, documents) and commits it to long-term storage without sufficient sanitization…

The paper describes indirect prompt-injection chains in agentic coding assistants where untrusted repository content, skill definitions, extension context, or MCP tool metadata is interpreted as instructions. Its novel skill-chain analysis identifies a concrete authorization weakness: skills can grant broad tool types such as Read or Bash without restricting permitted file targets, allowing repository-supplied instructions to influence sensitive reads or tool execution. The paper is a…