INSIGHT AI

Source-linked text edition ·

New Prompt Injection Techniques Cover Agent-Planning Attacks

The written, source-linked counterpart to this video.

Spoken scripts · Report and scripts (PDF)

Published edition1 story

New Prompt Injection Techniques Cover Agent-Planning Attacks

The CrowdStrike Prompt Injection Taxonomy, built and maintained by CrowdStrike AI security researchers, offers the industry's most comprehensive framework for understanding and defending against the ever-expanding array of attack techniques.

Today Crowdstrike is introducing a new version of the taxonomy that adds newly discovered attack techniques on autonomous agents and how they plan.

Watch next
Watch the Crowdstrike release for patch notes and rollout issues.

Video edition · Markdown edition

Source ledger