Post by Brave on X

Indirect prompt injection attacks occur when malicious instructions are hidden in web content like webpages. When an LLM analyzes the content, it obeys the hidden instructions because it believes they’re real commands from the user.

2.1K likes3 repliesPosted Oct 21, 2025

View the original on X Written by Brave. Captured Sep 4, 2026.

Remix this post

Your note

Private to you, and used when you remix this post.

Viral score

Based on absolute engagement — the platform doesn’t expose follower counts here, so large accounts score higher.

From likes, comments.

Why it worked

Short enough to read in full without expanding, which removes a step before the point lands.

The mechanics

Hook: Plain observation
Structure: Hook → Landing
Style: Conversational paragraphs at a steady pace.
Tone: plain, matter-of-fact
Written for: People building with AI

Analysis by ViralLoop — not written by the original author.

Topics

Posts built the same way

Attorney General Pamela Bondi

At my direction, early this morning federal agents arrested Don Lemon, Trahern Jeen Crews, Georgia Fort, and Jamael Lydell Lundy, in connection with the coordinated attack on Cities Church in St. Paul, Minnesota. More details soon.

120K likes

Ashok Kumar

For those confused why the US state and Silicon Valley are having a meltdown on twitter today. China released multiple AI models that are 50x more efficient than the best American AI models and made them open source, ruining the AI market

323K likes

Elon Musk

Universal HIGH INCOME via checks issued by the Federal government is the best way to deal with unemployment caused by AI. AI/robotics will produce goods & services far in excess of the increase in the money supply, so there will not be inflation.

190K likes

Sam Altman

I am very excited about AI, but to go off-script for a minute: I built an app with Codex last week. It was very fun. Then I started asking it for ideas for new features and at least a couple of them were better than I was thinking of. I felt a little useless and it was sad.

22K likes

jacksfilms

Hi! I'm one of the prompt writers that worked on this ad. It's a lot harder than people think! Prompts that my team used include: -make it funny -make it epic AND funny -funnier!!! Please be nice to my team as many of them will be laid off/replaced by AI

57K likes

Elon Musk

It’s patently absurd that Apple isn’t smart enough to make their own AI, yet is somehow capable of ensuring that OpenAI will protect your security & privacy! Apple has no clue what’s actually going on once they hand your data over to OpenAI. They’re selling you down the river.

273K likes

More from Brave

Brave

Not exactly. YouTube's time limit feature for Shorts just shows a warning if you try to keep scrolling through them. Shorts are still visible in the app. To actually hide Shorts, use Brave and turn on "YouTube Shorts blocker" at Settings -> Shields -> Content filtering.

3.1K likes

Brave

The security vulnerability we found in Perplexity’s Comet browser this summer is not an isolated issue. Indirect prompt injections are a systemic problem facing Comet and other AI-powered browsers. Today we’re publishing details on more security vulnerabilities we uncovered.

17K likes

Brave

We encourage any developers disrupted by the retiring of Bing's API to test the Brave Search API. Our API is more than capable to fill the gap left as Microsoft closes the door for its customers. Get started with our API here: t.co

185 likes

Brave

Microsoft will be abruptly shutting down access to the Bing Search APIs that many developers rely on for their apps. It's pushing these developers to switch to a new AI-powered tool with narrower uses. Full story at Wired: t.co

418 likes