Agent Eng News

Saturday, September 26, 2026 · Past edition · 2 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

Lead stories
Safety, alignment & governance
Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection
The abstract warns that flawed harnesses can make indirect-prompt-injection defenses appear to fail—or succeed—at the wrong rate, and reports sharp corrections when identical traces are rescored.
Why it matters: Security results can be misleading if the harness fails to deliver the attack, scores the wrong behavior, or confuses defensive blocking with inability to use tools. The proposed checks make those evaluation failures harder to hide.
Original · arxiv (new tab)Read

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

Agent Eng News

Lead stories

Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection

Keep notes on the stories you read