PROMPT INJECTION
7 items
6 posts, 1 guide
Copilot for Word AI worm: hidden prompts in a Word document hijack Copilot, alter financial data and self-propagate across documents. What HN thinks.
Prompt injection is role confusion: models do not reliably tell instructions from tool output, user content or their own reasoning, so better prompts fail.
Prompt injection through a bank transfer memo: how a €0.02 transfer compromised a banking AI assistant, and the five defense layers agent builders need.
The ChatGPT for Google Sheets exfiltration report shows spreadsheet agents need permission ledgers: action-scoped, logged, revocable, and visible permissions.
Prompt injection in agent apps is an architecture problem. Practical defenses: data boundaries, structured handoffs, tool guardrails, and approval gates.
Set up Codex Chronicle on macOS: enable it, grant Screen Recording and Accessibility access, and understand data storage, privacy, prompt injection and fixes.
Prompt injection in CONTRIBUTING.md and AGENTS.md: AI coding agents read repo docs before opening PRs, so those files are now part of the security boundary.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.