Prompt Injections for Defense
This seems to work : Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to prevent it from taking harmful actions. The LLM responds by shutting down. Examples are a prompt that
Record details
Published: 12 August 2026
Source: Bruce Schneier — Schneier on Security
Category: Field notes
Topics: Military & security · Agents & autonomy
Retrieved: 13 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Autonomous weapons systems, killer robots and human dignity
OpenAlex · 6 December 2018
More on the OpenAI Agent’s Attack on Hugging Face
Bruce Schneier — Schneier on Security · 3 August 2026
Appeals Court Agrees with EFF that Building a Web Browser Doesn’t Violate the CFAA
EFF Deeplinks · 4 August 2026
Are the Ukraine and the Iran Wars Merging? (Robert Wright & Nikita Petrov)
Nonzero (Robert Wright) · 29 July 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 July 2026
Amazon and University of Michigan give robots a sense of touch
Amazon Science · 10 July 2026
How to cite this record
ethics.ai (12 August 2026), “Prompt Injections for Defense,” evidence record 18859, https://ethics.ai/record/18859 (originally published by Bruce Schneier — Schneier on Security).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.