EresusSecurity
AI Agent Security

Validate autonomous agent action boundaries before release.

Eresus tests how AI agents can be abused across user intent, tool permissions, memory, retrieval, approval flows, and API actions using realistic scenarios.

Book a security briefingAll services
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

Tool-use and API action boundaries
Memory, retrieval, and context poisoning flows
Approval path, human-in-the-loop, and policy bypass tests
Multi-agent orchestration and permission chains

Risk signals

Agent performs unauthorized action
Data exposure through memory or retrieval
Approval flow bypassed through prompt control
Unexpected production impact through tool chaining

Outcomes

Agent runtime risk map
Tool scope and policy recommendations
Prompt-to-action PoC evidence
Release-readiness security checklist
Engagement model

Not scanner output. Offensive work that produces proof.

01

Scope and objective

We align assets, workflows, user roles, testing windows, and safe operating boundaries before execution starts.

02

Expert validation

Eresus analysts validate exploitability and business impact instead of forwarding automated scanner output.

03

Proof, fix, retest

Each finding ships with evidence, impact, remediation guidance, and retest steps so teams can close risk quickly.

FAQ

The questions buyers want answered early.

What AI surfaces and architectures do you test?+
We test autonomous AI agents, LLM integrations, RAG semantic search pipelines, MCP servers, tool execution boundaries, serialized model files (.pkl, .joblib, .gguf, .onnx, .keras), and guardrail implementations.
Is this limited to simple prompt injection testing?+
No. While prompt injection is evaluated, our red team focuses on systemic abuse: privilege escalation via tool use, indirect injection from retrieved documents, model extraction, training data poisoning, and remote code execution via unsafe model deserialization.
How are findings translated into engineering actions for AI teams?+
We map each vulnerability to specific defensive guardrail rules, system prompt structural hardening, strict JSON schema validators for tool calling, context window isolation, or container sandboxing configurations.
What is the duration and pricing for an AI Security Assessment?+
Typical AI and agentic security assessments take between 7 to 20 business days based on agent tooling count, RAG datasource complexity, and custom model architectures. Pricing is scoped transparently per integration boundary.
Do you assess compliance with the EU AI Act and OWASP LLM Top 10?+
Yes. All tests evaluate the full OWASP Top 10 for LLM Applications and provide risk categorization mapped against EU AI Act high-risk system transparency and cybersecurity requirements.
Is retesting included for AI guardrail and prompt fixes?+
Yes. We re-run targeted adversarial jailbreak suites and tool boundary validation within 30 days to ensure patched guardrails cannot be bypassed with semantic permutations.

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.

Related proof

Research and advisories that support this service motion.

Research

AI Agent Traps: Web Attacks Against Agents

How hidden web content, poisoned context, and tool access can manipulate autonomous AI agents in real enterprise workflows.

Research

Beyond Jailbreaks: Contextual Red Teaming for Agentic AI

Why standalone jailbreak tests miss agent risk, and how to test indirect prompt injection, retrieval boundaries, tool permissions, and recovery in multi-step systems.

Research

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.

Advisory

Unauthenticated Remote Code Execution via Arbitrary Command Injection in MCPHub Server Registration

MCPHub accepts attacker-controlled command and args values during server registration and spawns them through STDIO, enabling full remote code execution on the host.

Advisory

Authentication Bypass via skipAuth Configuration Grants Full Admin Access in MCPHub

When skipAuth is enabled, MCPHub bypasses both authentication and admin authorization checks, allowing any unauthenticated user to access privileged API functionality.

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.

Book a security briefingRequest a scope review