Agent Eng News
· Past edition · 10 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Browse published editions
Filter by topic · Safety, alignment & governance
Safety, alignment & governance
Safety, alignment & governance
A proposed agent defense separates tool-output instructions from authority.
Why it matters: Untrusted tool responses can influence an agent without being authorized to command it.
Safety, alignment & governance
Researchers describe context exfiltration through malicious agent tools.
Keep notes on the stories you read
Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.
- Personal notes on the sources you read, tied to your account
- A Library to come back to, with export to Markdown, Notion or Obsidian
- AI questions and rewrites on accounts with AI tools enabled
How Reading + AI works