EresusSecurity
Model Security

Prove whether a model artifact is safe enough for production intake.

Eresus reviews pickle, PyTorch, ONNX, safetensors, GGUF, archive, and container artifacts from HuggingFace and private model repositories for supply-chain and runtime risk.

Best fit

This engagement creates value fastest for teams like these.

AI product and platform teams

Teams shipping LLM, RAG, MCP, agent, or model-intake workflows into internal or customer-facing environments.

Security leaders expanding into AI

Organizations that already run pentest programs and now need guardrail, prompt, and tool-abuse validation.

Teams that need explainable hardening

Groups that need policy, prompt, MCP, and runtime findings translated into concrete mitigations and release decisions.

Scope

Model artifact and archive intake
Pickle/PyTorch loading and code execution risk
ONNX external data and custom operator checks
AIBOM, hash, signature, license, and provenance

Risk signals

Code execution during model loading
External data paths escaping the model directory
Mutable artifacts caused by missing hash or signature
Secrets in model cards, notebooks, or config

Outcomes

Model intake risk report
Sentinel rule ID and evidence output
AIBOM and supply-chain checklist
CI/CD model intake gate recommendations
Model intake flow

Review model artifacts as executable supply chain, not passive files.

01

Problem

We identify where the model came from, how it loads, and where it will run.

02

Attack scenario

We test malicious pickle, custom operators, archive traversal, secrets, and dependency chains.

03

Proof

Evidence is tied to file paths, hashes, opcodes, AST nodes, manifests, or model metadata.

04

Delivery

Intake criteria, quarantine, signing, and retest steps are turned into release decisions.

FAQ

The questions buyers want answered early.

What AI surfaces do you test?+
We test prompts, agents, RAG flows, MCP servers, tool use, model intake, and policy boundaries around real user workflows.
Is this just prompt injection testing?+
No. Prompt injection is one layer. We also validate identity, tool permissions, data leakage, model artifacts, and cross-system abuse paths.
Do you translate findings into engineering actions?+
Yes. We map each issue to guardrail changes, prompt updates, identity boundaries, tool scopes, or rollout decisions.

We tie risk to business impact.

Findings do not stop at severity labels. We explain which customer workflow, data class, or operational objective is affected.

Deliverables work for engineers and executives.

Engineering teams get reproducible proof and remediation direction; leadership gets the risk narrative, priority, and closure status.

Next step

Let’s scope this work against the surface that matters most.

Whether this starts as a pilot, a single application, a critical API, an AI agent flow, or a wider program, we start from the highest-impact surface.