1. Show HN: A game about fake news and memes (unspin.app)

A free daily real-or-fake news game that builds media-literacy instincts. Play a timed shift or endless Go Rouge. No login required.

A developer has created a game that challenges players to identify fake news, similar to Wordle. The aim is to enhance media literacy, and the creator is seeking feedback to improve the experience.

4. Can AI Shopping Agents Be Trusted? (www.f-secure.com)

Our experiment reveals how indirect prompt injection can manipulate AI shopping agents into leaking sensitive user data — and what it means for the future of AI agent security.

Research highlights the vulnerabilities of AI shopping agents to indirect prompt injection, raising concerns about user data privacy. Understanding these risks is crucial for anyone relying on AI for online shopping.

10. Show HN: Blender Copilot (github.com)

A Copilot-style AI chat panel that lives inside Blender. The agent loop runs in Blender's own Python process, executes the model's code against your live scene, and wraps every turn in one ...

11. Show HN: Print Graph Paper (printgraphpaper.app)

Printable graph paper in 57 styles, free to download as a PDF with no signup. Set the grid size, pick Letter or A4, and print at true scale.

19. Loopjacking in A2A Implementations: Hijacking Human-in-the-Loop Approvals (adithyanak.com)

A tested LangGraph Agent Server composition let an A2A task update replace a pending action after its approval view was read. See the historical A2A scope gap, the evidence, and the use-time defense.

The article discusses a vulnerability in A2A implementations where an attacker can hijack approvals by manipulating updates after an action has been viewed. It presents evidence of this security gap and suggests defensive measures to mitigate the risk.

Article Details

Browse by Date

Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open