https://sahnoun11.github.io/Oussama SahnounCybersecurity blog by Oussama Sahnoun. Focused on penetration testing, red teaming, and threat research, sharing insights, tutorials, and security guides for professionals and enthusiasts. 2026-09-18T15:50:41+01:00 Sahnoun_Oussama https://sahnoun11.github.io/ Jekyll © 2026 Sahnoun_Oussama /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png AI Agents & Tool Abuse — When the Blast Radius Moves at Machine Speed2026-09-17T09:00:00+01:00 2026-09-18T15:50:04+01:00 https://sahnoun11.github.io/posts/ai-agents-and-tool-abuse/ Sahnoun_Oussama Part 4 of the AI Systems Security Specialist series: agent autonomy as a risk multiplier — the confused deputy at machine speed, MCP as an attack surface, tool poisoning and rug pulls, memory poisoning, multi-agent trust, and the real 2026 agent incidents. Secure AI Systems Engineering — Building So That Being Fooled Doesn't Matter2026-09-10T09:00:00+01:00 2026-09-13T07:48:26+01:00 https://sahnoun11.github.io/posts/secure-ai-systems-engineering/ Sahnoun_Oussama Part 3 of the AI Systems Security Specialist series: the 2026 state of the art in defending AI systems — information-flow control, dual-LLM patterns, spotlighting, deterministic egress control, capability scoping, and the honest answer to whether prompt injection can be solved. Prompt Injection & Abuse Techniques — Attacking the Architecture2026-09-03T09:00:00+01:00 2026-09-03T16:15:59+01:00 https://sahnoun11.github.io/posts/prompt-injection-and-abuse-techniques/ Sahnoun_Oussama Part 2 of the AI Systems Security Specialist series: direct and indirect prompt injection, tokenizer-level filter evasion, multi-modal payloads, system prompt extraction, and the exfiltration channels that turn a text bug into a data breach — built around real 2025–2026 incidents including EchoLeak. AI/LLM Systems & Security Architecture — The Foundation Every AI Security Assessment Starts From2026-08-27T09:00:00+01:00 2026-08-27T21:17:09+01:00 https://sahnoun11.github.io/posts/ai-llm-systems-and-security-architecture/ Sahnoun_Oussama Part 1 of the AI Systems Security Specialist series: the complete architecture of an LLM application — tokens, context windows, inference, the five-layer stack, orchestrators, RAG, embeddings, trust boundaries and sensitive data flows — plus a full worked security review of a vulnerable RAG chatbot. The AI Systems Security Specialist — Series Overview2026-08-20T09:00:00+01:00 2026-08-20T09:00:00+01:00 https://sahnoun11.github.io/posts/ai-systems-security-specialist-series-overview/ Sahnoun_Oussama A nine-part weekly series on securing AI systems — from tokens and context windows to trust boundaries, agent tool abuse, red teaming, governance, and the AI-assisted SOC.