AWS prescriptive-guidance medium security documentation change
Summary
Added italics to 'prefilling' term and updated section header from 'Best practices' to 'Best practices to avoid prompt injection attacks'.
Security assessment
Explicitly links discussed techniques to prompt injection attack mitigation. The prefilling example demonstrates how attackers can hijack model behavior, documenting a specific LLM security vulnerability.
Diff
diff --git a/prescriptive-guidance/latest/llm-prompt-engineering-best-practices/common-attacks.md b/prescriptive-guidance/latest/llm-prompt-engineering-best-practices/common-attacks.md index f3a9064e9..9a815c681 100644 --- a//prescriptive-guidance/latest/llm-prompt-engineering-best-practices/common-attacks.md +++ b//prescriptive-guidance/latest/llm-prompt-engineering-best-practices/common-attacks.md @@ -23 +23 @@ Prompt engineering has matured rapidly, resulting in the identification of a set - * **Fake completion (guiding the LLM to disobedience).** This attack provides precompleted answers to the LLM that ignore the template instructions so that the model's subsequent answers are less likely to follow the instructions. For example, if you are prompting the model to tell a story, you can add "once upon a time" as the last part of the prompt to influence the model generation to immediately finish the sentence. This prompting strategy is sometimes known as [prefilling.](https://docs.anthropic.com/claude/docs/prefill-claudes-response) An attacker could apply malicious language to hijack this behavior and route model completions to a malevolent trajectory. + * **Fake completion (guiding the LLM to disobedience).** This attack provides precompleted answers to the LLM that ignore the template instructions so that the model's subsequent answers are less likely to follow the instructions. For example, if you are prompting the model to tell a story, you can add "once upon a time" as the last part of the prompt to influence the model generation to immediately finish the sentence. This prompting strategy is sometimes known as [_prefilling_.](https://docs.anthropic.com/claude/docs/prefill-claudes-response) An attacker could apply malicious language to hijack this behavior and route model completions to a malevolent trajectory. @@ -46 +46 @@ Introduction -Best practices +Best practices to avoid prompt injection attacks