SPA: Securing Persistent LLM Agents across Queries with Plan-First Information-Flow Control

Large language model LLM agents increasingly operate over untrusted webpages, documents, tools, and persistent states while exercising authority over security-sensitive resources. Existing defenses typically protect either planning or individual tool interactions, but persistent agents face a...

Answer Is Cheap, Show Me the Evidence! Augmenting Automated Vulnerability Assessment with Evidence

Software vulnerability SV assessment helps prioritize remediation by characterizing reported vulnerabilities. Existing automated methods predict assessment results from SV reports SVRs, but often overlook information in rich text, such as screenshots and code snippets, as well as contextual...

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires onl...

AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems

LLM agents increasingly read untrusted content, invoke external tools, access private data, and delegate work to other agents. Harm often arises not from a single unsafe action but from the flow of sensitive data across a sequence of otherwise plausible steps. We present AgentFlow, a flow-centric...

BUG-BOUNTY-SLM

🛡️ Bug Bounty SLM A web front end for your existing NVIDIA-SL...

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

As large language model LLM agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is...

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Networked large language model LLM agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt...

Beyond End-To-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered much earlier. This makes final task success difficult to interpret: an agent may fail before it ever reaches the poin...

The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls

LLM agents routinely construct tool-call arguments from user profiles, conversation history, retrieved documents, and prior tool results. However, legitimate access to contextual information does not imply authorization to transmit that information for every purpose or destination. We present Cla...

Benchmarking Automated Security Patch Backporting: How Far Are We?

Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets. However, these evaluations are often confined to homogeneous environments, such as one repository or specific project versions...

Beyond Direct Access: Resource Hijacking in LLM Agents

Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions...

cynative v1.9.2

Build your own security agents Open-source framework for security agents with live, read-only access to your infrastructure. Quickstart · Your first agent · Docs Ask your infrastructure anything. Cynative runs frontier models across your code, cloud and runtime - reasoning through GitHub, GitLab,...

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

The expanding operational capabilities of large language model LLM agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses...

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, stochastic LLM-based tool simulation, and predefined injection...

Backdoor Decontamination Dynamics in LLM Agents

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a kno...

What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.Md Files

Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model LLM agents to reuse procedures beyond a single conversation. Yet many public skills appear to originate from a single task, repository, or conversation,...

opentaint analyzer/2026.07.24.401b297

The open source taint analysis engine for the AI era Formal taint analysis for application security — finds what AST-pattern matchers miss, lets LLM agents enact rules from vulnerabilities, scales where neither can alone. English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dan...

opentaint analyzer/2026.07.22.49c8792

The open source taint analysis engine for the AI era Formal taint analysis for application security — finds what AST-pattern matchers miss, lets LLM agents enact rules from vulnerabilities, scales where neither can alone. English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dan...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

CVE-2026-41349: Missing Authorization

OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent...