EresusSecurity
Research & Intelligence

Eresus research, advisory, and security news

We collect writing, advisories, and current-event analysis around AI security, the MCP ecosystem, application security, and real attack chaining here.

Advisory Analysis · 3Guide · 1News · 3Research · 100

Latest Posts

Security Advisories

ERESUS-ADV-2026-002: Server-Side Request Forgery (SSRF) via Cloud Metadata Endpoints

Analysis of widespread SSRF vulnerabilities in cloud environments (AWS, GCP, Azure) exposing critical metadata endpoints and credentials.

2026-03-28Read
Security Advisories

Critical RCE Vulnerability in Legacy Enterprise Gateway

Critical Remote Code Execution (RCE) vulnerability in a legacy enterprise API gateway allowing unauthenticated root access.

2026-03-15Read
Insights

Hacking Humans: Social Engineering and the Psychology

Social engineering engagements are the most exciting and heart pumping. It doesn’t begin at the badge reader or the front desk. The access occurs when someone makes a decision.

2026-01-23Read
Red Teaming

Automated Red Teaming Scans of Agentic Workflows Using Eresus Sentinel

We are thrilled to announce the integration of Eresus Sentinel with Enterprise Agents, a groundbreaking step in securing LLM application deployments.

2026-04-27Read
GenAI

Strengthening AI Security with Eresus Security Defense Services

As organizations rapidly adopt generative AI, they face a new frontier of security challenges that traditional testing approaches simply cannot address.

2025-08-08Read
Threat Intelligence

Llama 4 Series Vulnerability Assessment: Scout vs. Maverick

Meta has launched the Llama 4 family, featuring models built on a mixture-of-experts (MoE) architecture. Here is our vulnerability assessment.

2025-07-16Read
Adversarial ML

AI Risk Report: Fast-Growing Threats in AI Runtime

A comprehensive look into the fast-growing vulnerabilities affecting AI systems in runtime environments, featuring Eresus Sentinel.

2026-04-27Read
GenAI

The Cost of Being Wordy: Detecting Resource-Draining Prompts

The breakthrough of LLMs has captivated the NLP world, but resource-draining prompts can cause Denial of Wallet (DoW) attacks in cloud models.

2025-06-17Read
Secure by Design

Tools and Technologies for Secure by Design AI Systems

Examining the specialized tools and technologies needed to secure non-deterministic, probabilistic AI systems effectively.

2025-04-16Read