Story · Semantic Scholar

Evaluating Indirect Prompt Injection Defenses in Tool-Using LLM Agents: Security, Utility, and Replication (Semantic Scholar)

paper · Story page

Four defenses and an undefended control ran on the AgentDojo banking benchmark across GPT-5.4, GPT-5.4-mini, and Claude Sonnet 4.6, with two independent replications (Tool Filter was tested only on the OpenAI models). On GPT-5.4-mini two defenses were associated with lower attack rates and lower benign utility, and none of the four paired comparisons survived Holm correction.

In plain words

  • Researchers tested ways to protect artificial intelligence (AI) assistants from malicious instructions hidden in material they read.
  • The attacks try to make an assistant follow instructions in outside content instead of its assigned task.
  • For one tested system, some protections were linked to fewer successful attacks but worse performance on ordinary tasks.
  • For people choosing protections, the apparent security improvements remained uncertain after researchers adjusted their calculations for testing several options.

Appeared in

Subscribe

Get the brief in your inbox

Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.

  • Weekdays at 8:45am IST, one lead story and 6 to 9 items.
  • Sundays, an argued synthesis rather than a recap.
  • One click to leave, and quiet days say so in the subject line.
How often

Weekdays 8:45am IST + Sundays. Unsubscribe in one click.

You're asking for The Agentic Brief by email at the cadence you picked. You can unsubscribe in one click from any issue, and your address is never sold or shared.