Indirect Prompt Injection via YouTube Transcripts (via) The first example I’ve seen in the wild of a prompt injection attack against a ChatGPT plugin—in this case, asking the VoxScript plugin to summarize the YouTube video with ID OBOYqiG3dAc is vulnerable to a prompt injection attack deliberately tagged onto the end of that video’s transcript.
Recent articles
- What happens if AI labs train for pelicans riding bicycles? - 13th November 2025
- Reverse engineering Codex CLI to get GPT-5-Codex-Mini to draw me a pelican - 9th November 2025
- Video + notes on upgrading a Datasette plugin for the latest 1.0 alpha, with help from uv and OpenAI Codex CLI - 6th November 2025