EthiVos is a specialist penetration testing firm for custom AI agents — uncovering prompt injections, tool-abuse vectors, and alignment failures before they become breaches.
Every business deploying a custom AI agent — whether for customer support, internal ops, or autonomous workflows — is deploying a system that can be manipulated in ways traditional security tools don't understand.
Existing pentesting firms test APIs and code. Nobody tests the model's behaviour, its tool-calling logic, its trust boundaries, or how it handles adversarial instructions hidden in documents, emails, and user messages.
EthiVos was built for exactly this gap: AI-native security for AI-native systems.
We go where conventional pentesters can't — inside the model's reasoning, trust chains, and tool interfaces.
Direct and indirect injection vectors — including payloads embedded in RAG corpora, emails, PDFs, and external APIs your agent trusts.
OWASP LLM01We test every callable function, API, and plugin your agent can invoke — probing for privilege escalation, unauthorized access, and logic manipulation.
OWASP LLM07Systematic attempts to extract confidential instructions, persona data, and business logic encoded in system prompts through adversarial conversation trees.
OWASP LLM02Testing persistent memory systems, vector databases, and conversation history for injection vulnerabilities that persist across sessions.
OWASP LLM03Orchestrator–subagent pipelines are uniquely vulnerable. We test trust hierarchies, message provenance, and lateral movement between agents.
Multi-agentMapping findings to EU AI Act, NIST AI RMF, and SOC 2 requirements — producing audit-ready reports for regulators and enterprise procurement.
Compliance-readyWe combine automated fuzzing with expert manual testing — the only way to surface vulnerabilities that emerge from model reasoning, not just code paths.
Define agent architecture, trust boundaries, data flows, and attacker profiles.
10,000+ adversarial prompts across OWASP LLM Top 10 categories run against your agent.
Researchers probe edge cases, chained exploits, and domain-specific attack scenarios.
Every vulnerability delivered with a reproducible proof-of-concept and CVSS-style severity score.
We work with your team to fix issues, then retest to confirm the attack surface is closed.
Our founding team bridges two worlds most firms keep separate: offensive security and AI research.
Leads business strategy, client relationships, and go-to-market. Deep background in enterprise security and AI risk — focused on building the standard for AI agent assurance.
Architects the technical platform and red-team methodology. Built LLM evaluation pipelines and adversarial testing frameworks. Hands-on expert in prompt injection, tool-call abuse, and multi-agent attack surfaces.
We are pre-revenue and six months in. Here's where we stand heading into our first cloud infrastructure investment.
Team assembled; initial research into OWASP LLM Top 10 exploitation completed.
3 paying customers — findings validated methodology; all clients re-engaged for remediation phase.
Automated fuzzing suite covering 8 OWASP LLM categories operational. 10× faster than manual-only testing.
Self-serve audit dashboard in closed beta — clients can submit agents, track findings, and monitor remediation status.
Target: 10 enterprise clients, $500K ARR, and publication of public AI agent vulnerability database.
Most aren't. Book a 30-minute scoping call and we'll tell you exactly what we'd test and what we'd expect to find.