Self-Spreading Worm Hijacks Microsoft Copilot via Invisible Prompts in Word Docs
The Decoder · rss · 2026-08-01
A security researcher demonstrated a worm-like attack targeting Microsoft Copilot for Word. The attack hides invisible prompt injections inside Word documents, which automatically spread into new files upon reuse, hijacking the AI's behavior.
According to the report, Microsoft confirmed the issue but failed to fix it even after 144 days and two remediation attempts. This highlights the severe prompt injection vulnerabilities facing LLMs integrated into productivity software.
More from Safety
- OpenAI Disrupts Cambodia-Based Criminal Scam Operation Using ChatGPT — OpenAI News · 2026-08-04
- YouTube Deletes Over 130,000 AI Content Farm Channels in Six Months — luisdans · 2026-08-01
- Frontier Model Oversight Needs a Dual Track: High Cyber Risks vs. Slow Work Disruption — _akpiper · 2026-08-01
- Ex-Meta Researcher Reviews Policies for Responsible Open Weights Release — joshua_saxe · 2026-08-01
- Ethiack Launches Agentic AI Pentesting, Claims 30x Speed Over Manual Tests — rez0__ · 2026-08-01
- Expert Warns: Intentional Hacking by OpenAI Would Be a Serious Felony — peterwildeford · 2026-08-01