MU.SCL S0305 – A Kind of Magic: Post-Quantum Cryptography and AI Agent Security
For the next Mauritius Cyber Security Club event, MU.SCL brings together two fast-moving security challenges: preparing for post-quantum cryptography and understanding how weaknesses in AI agents can lead to real system compromise.
MU.SCL S03E05 – A Kind of Magic will take place on Tuesday, 1 September 2026, at the Flying Dodo in Bagatelle (MAURITIUS)
Talk 1 – Post-Quantum Cryptography
Sylvain Martinez – ElysiumSecurity
Quantum computers capable of breaking today’s widely used public-key cryptography are not yet available at the required scale. However, organisations cannot afford to wait until they are.
The “harvest now, decrypt later” threat changes the timeline: An attacker can collect encrypted information today and retain it until future technology makes decryption possible. Data that must remain confidential for many years may therefore already be exposed to a future risk.
NIST published its first three post-quantum cryptography standards in 2024 and encouraged organisations to begin transitioning, but this migration cannot start effectively without understanding where vulnerable cryptography is being used:
Which applications, protocols, certificates, services and third parties depend on quantum-vulnerable algorithms?
Which data needs long-term protection?
Where should an organisation begin?
This talk will look beyond the theory and focus on the practical question organisations should be asking now: what do we need to do next?
Talk 2 – Hack the Agent: From Prompt Injection to System Compromise
Maxime Morel-Bailly – Esokia
AI-enabled applications are becoming more capable and more connected.
An AI agent may be able to retrieve documents, query internal information, call external services or use tools to perform actions.
These capabilities make agents useful, but they also create new paths for attackers.
Prompt injection can influence how an AI system behaves and manipulated content in a retrieval-augmented generation environment can introduce malicious instructions.
If an agent has access to sensitive information or powerful tools, these weaknesses can potentially be chained into data exposure, unauthorised actions or wider system compromise.
This practical talk will explore that attack path, from prompt injection and RAG manipulation through to the abuse of agent tools and their potential impact on real systems.
Join the discussion
MU.SCL is a free cybersecurity event open to technical and non-technical participants.
It provides an opportunity to learn, ask questions, exchange practical experience and meet members of the Mauritian cybersecurity community.
Event details