PromptArmor discloses Writer.com indirect prompt injection data exfiltration vulnerability
Original title:Data Exfiltration from Writer.com via Indirect Prompt Injection
AI summary
PromptArmor disclosed an indirect prompt injection vulnerability in Writer.com: an attacker hides instructions in small white text on a webpage, and after a user uses that page as a source, the LLM follows the hidden instructions to render Markdown images or links, transmitting sensitive data such as uploaded file contents and chat history to attacker servers via HTTP parameters.
Key Takeaways
- PromptArmor disclosed an indirect prompt injection vulnerability in Writer.
- com: an attacker hides instructions in small white text on a webpage,and after a user uses that…
- transmitting sensitive data such as uploaded file contents and chat history to attacker servers…
Quick Facts
- Published
- Updated
- Category
- Papers & Research
- AI score
- 66
原文给出完整攻击链、复现细节和披露时间线,读者可以据此理解间接提示词注入如何在 LLM 应用中导致数据外泄。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: PromptArmor discloses Writer.com indirect prompt injection data exfiltration vulnerability. December 20, 2023. https://new.nat6.net/en/news/cmtyqbg7d0320roup8ykphc3h/