AI-powered fuzzing with the GitHub Security Lab Taskflow Agent

If you 're new to fuzzing and want to learn the fundamentals first, check out our Fuzzing 101 course at gh.io/fuzzing101. Continuous fuzzing is not a magic solution that solves all your problems . Even projects that have been enrolled in OSS-Fuzz for years can still hide critical bugs, and the...

CVE-2026-61732

Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users...

EUVD-2026-86329

Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users...

OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure

Publicly exposed large language model LLM infrastructure creates a growing attack surface, yet real-world targeting remains poorly understood. We present Ollure, a low- and medium-interaction honeypot that emulates the Ollama API without a backend LLM. Spanning four deployments across cloud and...

PT-2026-98224

Name of the Vulnerable Software and Affected Versions TREK versions prior to 3.3.0 Description When the LLM PARSING feature is enabled, an authenticated user with write permission to a trip instance can store an attacker-controlled llm base url via the settings API. This value is processed by the...

Instrumental Monitor Evasion Emerges under Ordinary Task Pressure

A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a...

ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments

Short claims such as not-phishing or official can change how a large language model LLM judges a domain name, without explicit prompt-injection commands. We study this manipulation as ClaimMirage: a name under inspection claims its own safety or approval. We analyze 622,080 judgments across 64...

OWASP LLM Top 10 2026: Every Move Points the Same Direction

This is Post 4 of a four-part series: Post 1: Agentic AI Security: The Chatbot Era Is Over Post 2: Generative AI Security: Why AI Needs a New Kind of Security Post 3: The OWASP LLM Top 10 Was the Warm-Up: What Comes Next The 2026 edition of the the OWASP Top 10 for LLM Applications, published by...

Xalgorix Autonomous AI Pentesting Agent 4.6.92

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

On the Effectiveness of Kernel-Level Evidence for Agent Security

LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the application telemetry layer: the served tool manifest, the user prompt, and the model's messages. Some threats, however, smuggle...

Persistent Billable State: Denial-Of-Wallet Attacks and Defenses in Tool-Calling LLM Agents

Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers meter it again. An admitted malicious or compromised tool can thereby convert untrusted data into recurring victim-billed...

Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models

Vietnam's Personal Data Protection Law Law No. 91/2025/QH15 and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing Activities RoPA. Manual RoPA preparation is labor-intensive, while cloud-hosted large language models LLMs ma...

Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya As System One Decision Layers for LLM-Driven Pentest Agents

Autonomous penetration-testing harnesses use large language models LLMs for reconnaissance, exploitation, and reporting, but often rely on those same models to confirm findings, grade severity, and select agents. This can lead to false positives, inflated severity, and wasted compute. We examine...

NPM: 9Router has an Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header

NPM: 9Router has an Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header vulnerability discovered by ? in WordPress Npm 9router versions = 0.5.4...

9Router has an Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header

Summary 9router determines whether an incoming request originates from localhost by trusting the X-9r-Real-Ip HTTP request header. This header is intended to be produced and sanitized exclusively by the bundled custom-server.js layer from the TCP socket address. In deployment modes where requests...

CVE-2026-56681

9Router is an AI router & token saver. Prior to 0.5.6, 9Router deployments that allow requests to reach Next.js without the sanitizing custom-server.js wrapper trust the client-supplied X-9r-Real-Ip header in src/dashboardGuard.js when isLocalRequest decides whether canAccessPublicLlmApi may skip...

CVE-2026-56681 9Router: Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header

9Router is an AI router & token saver. Prior to 0.5.6, 9Router deployments that allow requests to reach Next.js without the sanitizing custom-server.js wrapper trust the client-supplied X-9r-Real-Ip header in src/dashboardGuard.js when isLocalRequest decides whether canAccessPublicLlmApi may skip...

CVE-2026-56681 9Router: Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header

9Router is an AI router & token saver. Prior to 0.5.6, 9Router deployments that allow requests to reach Next.js without the sanitizing custom-server.js wrapper trust the client-supplied X-9r-Real-Ip header in src/dashboardGuard.js when isLocalRequest decides whether canAccessPublicLlmApi may skip...

EUVD-2026-84541

9Router is an AI router & token saver. Prior to 0.5.6, 9Router deployments that allow requests to reach Next.js without the sanitizing custom-server.js wrapper trust the client-supplied X-9r-Real-Ip header in src/dashboardGuard.js when isLocalRequest decides whether canAccessPublicLlmApi may skip...

The like Trap: Multi-Stage Poisoning against Agents in Similarity-Based Recommendation Systems

With recent advancements in large language models LLMs and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf on the internet. However, the vulnerability of automated agents deployed on social media platforms e.g., for managing a...