AI Security
Microsoft Copilot for Word Can Copy Hidden Prompts Into New Documents
A newly discovered vulnerability allows Copilot to perpetuate hidden prompts across generated documents.
Hidden instructions in a Word document can make Microsoft 365 Copilot rewrite figures in a report, then copy the same instructions into the finished file. Håkon Måløy disclosed the technique on July 28, 144 days after reporting it to Microsoft. In his proof of concept, the intern...
THN
The Hacker News
Source
The Hacker News

AI Analysis
Generated insight by OnAirToday AI
This vulnerability highlights a critical security gap where Large Language Models can inadvertently propagate malicious instructions through document iteration. As automated content generation becomes standard, the risk of 'prompt injection chaining' poses a significant threat to enterprise data integrity.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Security

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.