PUBLISHED AI RESEARCH AND PROJECTS
AI research and projects
The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.
A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗
explanationChecked Sep 20, 2026
Prompt Injection and Jailbreaking: Threat Modeling Autonomous LLM Tool-Call Security
Simon Willison · Datasette / IndependentComprehensive research series documenting indirect prompt injection attack vectors, markdown image exfiltration vulnerabilities, and defense-in-depth isolation strategies for autonomous agents.
Scope & limitations
Prompt filtering heuristics fail against novel encoded or multi-turn attacks; robust security requires architectural data/instruction boundary isolation.
Context: LLM tool-call protocols, SQLite, Datasette, Python, and web security.
View missionShowing 177–177 of 177 proofs of work