https://www.lynneredteamlog.tech/learning-log/ Recent content in Learning Log on AI Red Team Log Hugo en-us Mon, 10 Aug 2026 00:00:00 +0000 https://www.lynneredteamlog.tech/learning-log/week-04-insecure-output-handling/ Mon, 10 Aug 2026 00:00:00 +0000 https://www.lynneredteamlog.tech/learning-log/week-04-insecure-output-handling/ Building a toy XSS demo to understand why LLM output shouldn’t be trusted downstream, then tracing how this plays out in real CVEs and NVR-style natural language query systems. https://www.lynneredteamlog.tech/learning-log/week-01-owasp-llm-top-10/ Sun, 05 Jul 2026 00:00:00 +0000 https://www.lynneredteamlog.tech/learning-log/week-01-owasp-llm-top-10/ Testing three prompt injection techniques against two local LLMs (Llama 3 8B and Mistral 7B) — direct override, roleplay jailbreak, and encoding obfuscation — to see how they hold up. https://www.lynneredteamlog.tech/learning-log/week-02-rag-architecture/ Mon, 01 Jan 0001 00:00:00 +0000 https://www.lynneredteamlog.tech/learning-log/week-02-rag-architecture/ Reviewing the two phases of my RAG pipeline — indexing and query — and drawing out the full data flow. https://www.lynneredteamlog.tech/learning-log/week-03-rag-pipeline/ Mon, 01 Jan 0001 00:00:00 +0000 https://www.lynneredteamlog.tech/learning-log/week-03-rag-pipeline/ Testing whether a RAG pipeline can be hijacked by an instruction hidden inside a retrieved document — and why a task-specific prompt template may accidentally provide some resistance.