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...

Highly Autonomous Cyber-Capable Agents: Anticipating Capabilities, Tactics, and Strategic Implications

This report introduces the concept of "Highly Autonomous Cyber-Capable Agents" HACCAs, AI systems capable of autonomously conducting multi-stage cyber campaigns at a level comparable to today's top criminal hacking groups or state-affiliated threat actors, and analyzes the security implications o...

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...

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...

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...

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...

DEBIAN-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-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-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-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...

manchurian-agent-poc

Manchurian Candidate Agent POC ⚠️ SECURITY RESEARCH — EDU...

Agentic AI security: Why you need to know about autonomous agents now

Agentic AI is making headlines worldwide for its potential force-multiplying capabilities, and organizations are understandably intrigued by how it can improve throughput and capabilities. However, as with any technological revolution, unforeseen issues are inevitable, and agentic AI is no...

CVE-2026-3917: Use After Free

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-2026-30969

Coral Server is open collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. Prior to 1.1.0, Coral Server did not enforce strong authentication between agents and the server within an active session. This could allow an attacker who...

EUVD-2026-10706

Coral Server is open collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. Prior to 1.1.0, the SSE endpoint /sse/v1/... in Coral Server did not strongly validate that a connecting agent was a legitimate participant in the session. Th...

How to Stop AI Data Leaks: A Webinar Guide to Auditing Modern Agentic Workflows

Artificial Intelligence AI is no longer just a tool we talk to; it is a tool that does things for us. These are called AI Agents. They can send emails, move data, and even manage software on their own. But there is a problem. While these agents make work faster, they also open a new "back door" f...

PT-2026-24340

Name of the Vulnerable Software and Affected Versions Coral Server versions prior to 1.1.0 Description Coral Server, an open collaboration infrastructure for The Internet of Agents, did not enforce strong authentication between agents and the server during active sessions. This could allow an...

Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors

OpenClaw-style agent stacks turn language into privileged execution: LLM intents flow through tool interception, policy gates, and a local executor. In parallel, skill marketplaces such as skills.sh make capability acquisition as easy as installing skills and CLIs, creating a growing capability...

PT-2026-24339

Name of the Vulnerable Software and Affected Versions Coral Server versions prior to 1.1.0 Description Coral Server is an open collaboration infrastructure designed for communication, coordination, trust, and payments within The Internet of Agents. Before version 1.1.0, the Server Side Events SSE...

This Week in Spring - March 10th, 2026

Hi, Spring fans! Welcome to another installment of This Week in Spring. As I write this, I am preparing for a trip to Rust, Germany, for one of the best Java conferences in Europe: JavaLand, along with its new companion event, DevLand. It should be fun. Will you be around? If so, say hi. We have ...