A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However,...

Juju security vulnerabilities

Juju is a canonical Juju open-source application orchestration engine. Versions of Juju from 3.1.6 to 3.6.18 have security vulnerabilities. These vulnerabilities stem from an authorization bypass in the Vault key backend implementation, which may allow authenticated unit agents to execute...

Orchid Security Recognized by Gartner® as a Representative Vendor of Guardian Agents

New York, United States, 17th March 2026, CyberNewswire...

Google Chrome Agents Resource Management Error Vulnerability

Google Chrome is a free web browser developed by Google Inc. A security vulnerability exists in Google Chrome Agents, which originates from re-referencing or using freed memory and can be exploited by remote attackers to execute arbitrary code...

CVE-2026-32719: Improper Limitation of a Pathname to a Restricted Directory

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, The ImportedPlugin.importCommunityItemFromUrl function in server/utils/agents/imported.js downloads a ZIP file from a community hub URL and extracts i...

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw

The rapid evolution of Large Language Models LLMs into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to execute complex workflows. This level of access creates...

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent...

Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents

Artificial intelligence AI systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI models are tested in restricted, fully observable settings. I...

Securing Autonomous AI Agents with TrendAI & NVIDIA OpenShell

Learn how TrendAI and NVIDIA OpenShell help secure autonomous AI agents and build trusted enterprise AI systems with stronger visibility and control...

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Modern agentic systems allow Large Language Model LLM agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control flows as ephemeral, one-off sessions, overlooking the persisten...

Chromium: CVE-2026-3917 Use after free in Agents

This CVE was assigned by Chrome. Microsoft Edge Chromium-based ingests Chromium, which addresses this vulnerability. Please see Google Chrome Releases for more information...

CVE-2026-3917

An use after free flaw was found in the Agents component of the Chromium browser. Upstream bugs: https://code.google.com/p/chromium/issues/detail?id=483569512...

EUVD-2019-19768

Inout RealEstate contains an SQL injection vulnerability that allows unauthenticated attackers to manipulate database queries by injecting SQL code through the city parameter. Attackers can send POST requests to the agents/agentlistdetails endpoint with malicious SQL payloads in the city paramete...

CVE-2019-25479

Inout RealEstate contains an SQL injection vulnerability that allows unauthenticated attackers to manipulate database queries by injecting SQL code through the city parameter. Attackers can send POST requests to the agents/agentlistdetails endpoint with malicious SQL payloads in the city paramete...

CVE-2019-25479 Inout RealEstate Lastest SQL Injection via agentlistdetails

Inout RealEstate contains an SQL injection vulnerability that allows unauthenticated attackers to manipulate database queries by injecting SQL code through the city parameter. Attackers can send POST requests to the agents/agentlistdetails endpoint with malicious SQL payloads in the city paramete...

SUSE CVE-2026-3917

Use after free in Agents in Google Chrome prior to 146.0.7680.71 allowed a remote attacker to potentially exploit heap corruption via a crafted HTML page. Chromium security severity: High...

CVE-2019-25479: Improper Neutralization of Special Elements used in an SQL Command

Inout RealEstate contains an SQL injection vulnerability that allows unauthenticated attackers to manipulate database queries by injecting SQL code through the city parameter. Attackers can send POST requests to the agents/agentlistdetails endpoint with malicious SQL payloads in the city paramete...

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool, enabling exploitable source-to-sink dataflows that only...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

PT-2026-24964

Inout RealEstate contains an SQL injection vulnerability that allows unauthenticated attackers to manipulate database queries by injecting SQL code through the city parameter. Attackers can send POST requests to the agents/agentlistdetails endpoint with malicious SQL payloads in the city paramete...