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.

Guide · 27News · 4Case Study · 3Research · 84Technical Guide · 2Advisory Analysis · 5Advisory · 2

Latest Posts

Runtime Threats

LiteRT FlatBuffer Metadata RCE Exploits

Identifies critical threats leveraging the custom metadata extension fields within LiteRT (.tflite) FlatBuffer archives to force path traversals and...

2026-04-10Read
Deserialization Threats

Joblib Model Suspicious Code Execution Detected at Model Load Time

Identifies suspicious execution sequences during a Joblib model load indicating potentially obfuscated deserialization threats and runtime hooks.

2026-04-27Read
Deserialization Threats

PAIT-GGUF-101: Arbitrary Code Execution via Unsandboxed Jinja2 Chat Templates in GGUF Models

Detailed analysis of Server-Side Template Injection (SSTI) in GGUF LLM formats, explaining how malicious Jinja2 chat templates execute remote shell commands upon model load.

2026-04-10Read
Deserialization Threats

GGUF Metadata Parsing Flaws (Llama.cpp Buffer Overflows)

Identifies highly critical buffer overflow attacks manipulating the internal metadata and vocabulary tensors of GGUF files to exploit C++ parsers like...

2026-04-27Read
GuideCybersecurityOWASP Top 10 for LLM Applications

Automated Red Teaming for Agentic AI Workflows: What to Test and What to Measure

A practical framework for testing prompt injection, tool abuse, data exposure, excessive agency, and recovery in enterprise agent workflows.

2026-08-11Read
Deserialization Threats

Extraction-Triggered Environment Override (Path Overwriting)

An advanced attack where a malicious model archive weaponizes extraction processes to overwrite critical environment-level objects, seizing control of...

2026-04-27Read
GuideCybersecurityNIST AI Risk Management Framework

AI Security Testing for GenAI Applications: From Prompt Tests to Runtime Controls

A practical guide to assessing GenAI applications, agent permissions, RAG data flows, prompt injection, output handling, and runtime evidence.

2026-08-11Read
Deserialization Threats

Execution of Arbitrary Code via Model Config Architecture Targets

Identifying advanced threats where malicious executables are obfuscated as configuration objects inside an ML model archive, triggering Remote Code...

2026-04-27Read
Deserialization Threats

Joblib / Scikit-Learn Arbitrary Code Execution (ACE)

Identifies insecure object deserialization attacks utilizing the popular Scikit-Learn Joblib persistency library, granting attackers remote execution...

2026-04-27Read