AI Hack: The Prompt That Scans You For Vulnerabilities
- 153k
- views
- 45k
- baseline
- 5.2×
- engagement
- 9.7k
- likes
- 10k
- saves
- 3.5k
- shares
Why it beat the baseline
hook · on screen text“AI Hack: The Prompt That Scans You For Vulnerabilities”
talking-headutility
- Addresses online security fears from recent cyber events
- Proposes using local AI desktop apps defensively
- Dictates a specific copy-paste security audit prompt
- Validates with reactions from users who tried it
Why it worked. Provides an immediate, high-utility defensive AI prompt resolving heightened viewer anxiety around hacking.
Grounded in the actual video and audio; analyzed by gemini-3.8-flash, cached.
Video analysis
Every shot, the spoken script, on-screen text, audio, editing and a recreation blueprint, from the actual video and audio.
Structure · 93s
- 00:00.0–00:19.4Problem framing. Acknowledge recent security threat context and tease solution
- 00:19.5–00:38.0Prerequisites. Explain required local apps before running prompt
- 00:38.1–01:12.5Prompt dictation. Provide exact, actionable copy-paste prompt
- 01:12.6–01:33.2Proof and validation. Share real tester feedback and final call to protect oneself
Shot list
| # | time | shot | what is visible | spoken | on screen |
|---|---|---|---|---|---|
| 1 | 00:00.0–01:33.2 | close-up Front-facing smartphone camera static handheld; Subtle handheld micro-movements | Speaker speaking directly into camera with hand gestures | If you saw my video about the fact that the internet is burning down and AI is causing a bunch of hacks and you're wondering how to protect yourself, one of the things I want to tell you is that you can actually use AI to make that better. I know that might sound weird, but we would rather have AI working for defense than working on attack. So here is a prompt. It is a very short prompt that you can use and feed to Claude, you can feed it to ChatGPT. It's very simple. You want to have an installed app on your machine, so, uh, you know, ChatGPT worker Codex or Claude installed on your, on your desktop. And then what you say is this: 'Please scan my system, all of my online presence and projects, everything you could find about me online. Look for vulnerabilities. Specifically, look for vulnerabilities tied to established bugs, hacks, and zero-day vulnerabilities found during the Black October event, which is ongoing. Come back to me with a list of vulnerabilities stacked in priority order and a plan to fix them.' That's it. It is scary how much that will turn up, but in a good way because it means you can get safer. It will look at your whole internet presence, it really will. Look at your whole system. I have had people run this prompt and they come back saying, one, thank you, and two, I am horrified. So give it a try. Make yourself safer. Cheers. | AI Hack: The Prompt That Scans You For Vulnerabilities · IF YOU SAW · MY VIDEO ABOUT · THE INTERNET IS · BURNING DOWN · AND AI IS · CAUSING A BUNCH · OF HACKS · AND YOU'RE WONDERING · HOW TO PROTECT · YOURSELF, · ONE OF THE · THINGS I WANT TO · TELL YOU · IS THAT YOU · CAN ACTUALLY · USE AI · TO MAKE · THAT BETTER. · I KNOW THAT · MIGHT SOUND WEIRD, · BUT WE WOULD · RATHER HAVE AI · WORKING FOR DEFENSE · THAN WORKING ON · ATTACK. · SO HERE IS · A PROMPT. · IT IS A · VERY SHORT PROMPT · THAT YOU · CAN USE · AND FEED · TO CLAUDE, · YOU CAN FEED · IT TO CHATGPT. · IT'S VERY SIMPLE. · YOU WANT TO · HAVE AN INSTALLED · APP ON YOUR · MACHINE, · SO, · UH, YOU KNOW, · CHATGPT · WORKER CODEX, · OR CLAUDE · INSTALLED ON YOUR · ON YOUR · DESKTOP. · AND THEN · WHAT YOU SAY · IS THIS. · PLEASE SCAN MY · SYSTEM, · ALL OF · MY ONLINE PRESENCE · AND PROJECTS, · EVERYTHING · YOU COULD · FIND ABOUT ME · ONLINE. · LOOK FOR · VULNERABILITIES. · SPECIFICALLY, · LOOK FOR · VULNERABILITIES · TIED TO · ESTABLISHED · BUGS, · HACKS AND ZERO · DAY VULNERABILITIES · FOUND · DURING THE BLACK · OCTOBER EVENT, · WHICH IS ONGOING. · COME BACK TO · ME WITH A · LIST OF VULNERABILITIES · STACKED IN PRIORITY · ORDER · AND A PLAN · TO FIX THEM. · THAT'S IT. · IT IS SCARY · HOW MUCH THAT · WILL TURN UP, · BUT IN A · GOOD WAY BECAUSE · IT MEANS YOU · CAN GET SAFER. · IT WILL · LOOK AT YOUR · WHOLE · INTERNET PRESENCE. · IT REALLY WILL. · LOOK AT YOUR · WHOLE SYSTEM. · I HAVE HAD · PEOPLE RUN THIS · PROMPT · AND THEY · COME BACK SAYING, · ONE, THANK YOU, · AND TWO, · I AM HORRIFIED. · SO GIVE IT · A TRY. · MAKE YOURSELF · SAFER. · CHEERS. |
Script
- 00:00.0–00:07.5“If you saw my video about the fact that the internet is burning down and AI is causing a bunch of hacks and you're wondering how to protect yourself,” · Engaging, conversational setup
- 00:07.6–00:19.4“one of the things I want to tell you is that you can actually use AI to make that better. I know that might sound weird, but we would rather have AI working for defense than working on attack.” · Empathetic, reassuring
- 00:19.5–00:38.0“So here is a prompt. It is a very short prompt that you can use and feed to Claude, you can feed it to ChatGPT. It's very simple. You want to have an installed app on your machine, so, uh, you know, ChatGPT worker Codex or Claude installed on your, on your desktop. And then what you say is this:” · Instructive, preparatory
- 00:38.1–01:12.5“Please scan my system, all of my online presence and projects, everything you could find about me online. Look for vulnerabilities. Specifically, look for vulnerabilities tied to established bugs, hacks, and zero-day vulnerabilities found during the Black October event, which is ongoing. Come back to me with a list of vulnerabilities stacked in priority order and a plan to fix them.” · Slow, clear dictation
- 01:12.6–01:33.2“That's it. It is scary how much that will turn up, but in a good way because it means you can get safer. It will look at your whole internet presence, it really will. Look at your whole system. I have had people run this prompt and they come back saying, one, thank you, and two, I am horrified. So give it a try. Make yourself safer. Cheers.” · Earnest conclusion with social proof and sign-off
On-screen text
- 00:00.0–01:33.2“AI Hack: The Prompt That Scans You For Vulnerabilities” · hook · top center · Blue rounded pill banner, bold white sans-serif text
- 00:00.5–01:32.8“Subtitles synchronized to speech” · caption · lower third center · Black capitalized font with turquoise highlight on current word
Recreation blueprint
One-take talking-head addressing a viral fear, explaining how to flip the tool defensively, and dictating a precise prompt.
| slot | s | visual | voiceover | overlay |
|---|---|---|---|---|
| Hook & Concept | 19.5 | Close-up talking head addressing an urgent tech threat | Reference recent fear event, introduce defensive AI countermeasure | Persistent banner naming the prompt/hack |
| Tool Setup | 18.5 | Same framing, speaker uses hand gestures to clarify prerequisites | Specify necessary client apps for local execution | Animated synced captions |
| Prompt Dictation | 34.5 | Speaker slows delivery, dictating exact instructions clearly | Dictate exact audit prompt verbatim | Highlighted captions tracking every dictated word |
| Social Proof & Sign-off | 20.7 | Speaker nods, leans back slightly, casual sign-off | Describe shocked beta user reactions and urge viewer to run it | Synced captions ending with final CTA |
Keep
- Continuous uncut direct-to-camera presentation
- Persistent top banner with clear utility hook
- Slow, copyable dictation of the exact prompt
- Word-by-word synced caption highlighting
Can change
- Target threat topic (finance, privacy, SEO)
- Specific AI desktop tool referenced
- Speaker appearance and location
Generation prompts per shot (1)
- Shot 1. Vertical 9:16 smartphone video close-up of a 40-year-old tech creator with glasses and beard speaking candidly to camera in home interior, natural daylight, single continuous take.
Negative: cinematic camera cuts, b-roll, background music, studio backdrop, oversaturated
Raw JSON (for a video pipeline)
{
"hook": {
"spoken": "If you saw my video about the fact that the internet is burning down and AI is causing a bunch of hacks and you're wondering how to protect yourself...",
"ends_at": "00:07.5",
"on_screen": "AI Hack: The Prompt That Scans You For Vulnerabilities",
"starts_at": "00:00.0",
"technique": "bold_claim",
"technique_note": "Contrasts a massive scary threat with a direct tactical defense",
"why_it_stops_the_scroll": "Pairs fear-inducing cybersecurity threats with an actionable, specific AI prompt solution."
},
"tags": {
"topics": [
"ai",
"cybersecurity",
"chatgpt",
"claude",
"prompting"
],
"cta_type": "other",
"language": "en",
"has_music": false,
"has_speech": true,
"content_type": "talking_head_advice",
"products_or_apps": [
"Claude",
"ChatGPT"
],
"has_burned_captions": true
},
"audio": {
"music": "None",
"voice": "Direct spoken male voice, conversational, clear diction",
"ambient": "Clean interior acoustic with negligible room reverb",
"mix_notes": "Dry, clean voice track prioritized",
"sound_effects": "None"
},
"shots": [
{
"end": "01:33.2",
"index": 1,
"start": "00:00.0",
"camera": "Front-facing smartphone camera static handheld",
"framing": "Vertical close-up from chest to top of head",
"movement": "Subtle handheld micro-movements",
"shot_type": "close-up",
"transition_in": "none",
"screen_content": "None",
"subject_action": "Gestures with hand while speaking and dictating prompt",
"what_is_visible": "Speaker speaking directly into camera with hand gestures",
"duration_seconds": 93.2,
"spoken_during_shot": "If you saw my video about the fact that the internet is burning down and AI is causing a bunch of hacks and you're wondering how to protect yourself, one of the things I want to tell you is that you can actually use AI to make that better. I know that might sound weird, but we would rather have AI working for defense than working on attack. So here is a prompt. It is a very short prompt that you can use and feed to Claude, you can feed it to ChatGPT. It's very simple. You want to have an installed app on your machine, so, uh, you know, ChatGPT worker Codex or Claude installed on your, on your desktop. And then what you say is this: 'Please scan my system, all of my online presence and projects, everything you could find about me online. Look for vulnerabilities. Specifically, look for vulnerabilities tied to established bugs, hacks, and zero-day vulnerabilities found during the Black October event, which is ongoing. Come back to me with a list of vulnerabilities stacked in priority order and a plan to fix them.' That's it. It is scary how much that will turn up, but in a good way because it means you can get safer. It will look at your whole internet presence, it really will. Look at your whole system. I have had people run this prompt and they come back saying, one, thank you, and two, I am horrified. So give it a try. Make yourself safer. Cheers.",
"on_screen_text_during_shot": [
"AI Hack: The Prompt That Scans You For Vulnerabilities",
"IF YOU SAW",
"MY VIDEO ABOUT",
"THE INTERNET IS",
"BURNING DOWN",
"AND AI IS",
"CAUSING A BUNCH",
"OF HACKS",
"AND YOU'RE WONDERING",
"HOW TO PROTECT",
"YOURSELF,",
"ONE OF THE",
"THINGS I WANT TO",
"TELL YOU",
"IS THAT YOU",
"CAN ACTUALLY",
"USE AI",
"TO MAKE",
"THAT BETTER.",
"I KNOW THAT",
"MIGHT SOUND WEIRD,",
"BUT WE WOULD",
"RATHER HAVE AI",
"WORKING FOR DEFENSE",
"THAN WORKING ON",
"ATTACK.",
"SO HERE IS",
"A PROMPT.",
"IT IS A",
"VERY SHORT PROMPT",
"THAT YOU",
"CAN USE",
"AND FEED",
"TO CLAUDE,",
"YOU CAN FEED",
"IT TO CHATGPT.",
"IT'S VERY SIMPLE.",
"YOU WANT TO",
"HAVE AN INSTALLED",
"APP ON YOUR",
"MACHINE,",
"SO,",
"UH, YOU KNOW,",
"CHATGPT",
"WORKER CODEX,",
"OR CLAUDE",
"INSTALLED ON YOUR",
"ON YOUR",
"DESKTOP.",
"AND THEN",
"WHAT YOU SAY",
"IS THIS.",
"PLEASE SCAN MY",
"SYSTEM,",
"ALL OF",
"MY ONLINE PRESENCE",
"AND PROJECTS,",
"EVERYTHING",
"YOU COULD",
"FIND ABOUT ME",
"ONLINE.",
"LOOK FOR",
"VULNERABILITIES.",
"SPECIFICALLY,",
"LOOK FOR",
"VULNERABILITIES",
"TIED TO",
"ESTABLISHED",
"BUGS,",
"HACKS AND ZERO",
"DAY VULNERABILITIES",
"FOUND",
"DURING THE BLACK",
"OCTOBER EVENT,",
"WHICH IS ONGOING.",
"COME BACK TO",
"ME WITH A",
"LIST OF VULNERABILITIES",
"STACKED IN PRIORITY",
"ORDER",
"AND A PLAN",
"TO FIX THEM.",
"THAT'S IT.",
"IT IS SCARY",
"HOW MUCH THAT",
"WILL TURN UP,",
"BUT IN A",
"GOOD WAY BECAUSE",
"IT MEANS YOU",
"CAN GET SAFER.",
"IT WILL",
"LOOK AT YOUR",
"WHOLE",
"INTERNET PRESENCE.",
"IT REALLY WILL.",
"LOOK AT YOUR",
"WHOLE SYSTEM.",
"I HAVE HAD",
"PEOPLE RUN THIS",
"PROMPT",
"AND THEY",
"COME BACK SAYING,",
"ONE, THANK YOU,",
"AND TWO,",
"I AM HORRIFIED.",
"SO GIVE IT",
"A TRY.",
"MAKE YOURSELF",
"SAFER.",
"CHEERS."
],
"facial_expression_or_gesture": "Expressive, wide eyes, touching chin, counting points with fingers"
}
],
"video": {
"pacing": "Deliberate, conversational talking-head",
"setting": "Indoor room, kitchen or home office background",
"subject": "Bearded adult male wearing glasses and plaid flannel shirt",
"lighting": "Natural daylight from front-left with interior warm rim",
"color_grade": "Natural warm indoor grade",
"orientation": "vertical",
"aspect_ratio": "9:16",
"overall_format": "talking-head",
"tone_and_energy": "Serious, informative, earnest",
"duration_seconds": 93.2,
"wardrobe_and_look": "Casual plaid shirt, dark round eyeglasses, graying beard"
},
"script": [
{
"end": "00:07.5",
"line": "If you saw my video about the fact that the internet is burning down and AI is causing a bunch of hacks and you're wondering how to protect yourself,",
"start": "00:00.0",
"delivery": "Engaging, conversational setup",
"uncertain": false
},
{
"end": "00:19.4",
"line": "one of the things I want to tell you is that you can actually use AI to make that better. I know that might sound weird, but we would rather have AI working for defense than working on attack.",
"start": "00:07.6",
"delivery": "Empathetic, reassuring",
"uncertain": false
},
{
"end": "00:38.0",
"line": "So here is a prompt. It is a very short prompt that you can use and feed to Claude, you can feed it to ChatGPT. It's very simple. You want to have an installed app on your machine, so, uh, you know, ChatGPT worker Codex or Claude installed on your, on your desktop. And then what you say is this:",
"start": "00:19.5",
"delivery": "Instructive, preparatory",
"uncertain": false
},
{
"end": "01:12.5",
"line": "Please scan my system, all of my online presence and projects, everything you could find about me online. Look for vulnerabilities. Specifically, look for vulnerabilities tied to established bugs, hacks, and zero-day vulnerabilities found during the Black October event, which is ongoing. Come back to me with a list of vulnerabilities stacked in priority order and a plan to fix them.",
"start": "00:38.1",
"delivery": "Slow, clear dictation",
"uncertain": false
},
{
"end": "01:33.2",
"line": "That's it. It is scary how much that will turn up, but in a good way because it means you can get safer. It will look at your whole internet presence, it really will. Look at your whole system. I have had people run this prompt and they come back saying, one, thank you, and two, I am horrified. So give it a try. Make yourself safer. Cheers.",
"start": "01:12.6",
"delivery": "Earnest conclusion with social proof and sign-off",
"uncertain": false
}
],
"editing": {
"cut_count": 0,
"transitions": "None (continuous take)",
"caption_style": "Word-by-word highlighted captions in lower third",
"end_card_or_cta": "Verbal: 'Give it a try. Make yourself safer. Cheers.'",
"average_shot_seconds": 93.2,
"effects_and_overlays": "Top sticky blue title card"
},
"teardown": {
"hook": "AI Hack: The Prompt That Scans You For Vulnerabilities",
"format": "talking-head",
"mechanism": "utility",
"structure": [
"Addresses online security fears from recent cyber events",
"Proposes using local AI desktop apps defensively",
"Dictates a specific copy-paste security audit prompt",
"Validates with reactions from users who tried it"
],
"hook_source": "on_screen_text",
"why_it_worked": "Provides an immediate, high-utility defensive AI prompt resolving heightened viewer anxiety around hacking."
},
"on_screen_text": [
{
"end": "01:33.2",
"kind": "hook",
"text": "AI Hack: The Prompt That Scans You For Vulnerabilities",
"start": "00:00.0",
"style": "Blue rounded pill banner, bold white sans-serif text",
"source": "creator overlay",
"position": "top center"
},
{
"end": "01:32.8",
"kind": "caption",
"text": "Subtitles synchronized to speech",
"start": "00:00.5",
"style": "Black capitalized font with turquoise highlight on current word",
"source": "burned captions",
"position": "lower third center"
}
],
"structure_beats": [
{
"end": "00:19.4",
"beat": "Problem framing",
"start": "00:00.0",
"purpose": "Acknowledge recent security threat context and tease solution"
},
{
"end": "00:38.0",
"beat": "Prerequisites",
"start": "00:19.5",
"purpose": "Explain required local apps before running prompt"
},
{
"end": "01:12.5",
"beat": "Prompt dictation",
"start": "00:38.1",
"purpose": "Provide exact, actionable copy-paste prompt"
},
{
"end": "01:33.2",
"beat": "Proof and validation",
"start": "01:12.6",
"purpose": "Share real tester feedback and final call to protect oneself"
}
],
"recreation_blueprint": {
"shot_template": [
{
"slot": "Hook & Concept",
"visual": "Close-up talking head addressing an urgent tech threat",
"seconds": 19.5,
"voiceover": "Reference recent fear event, introduce defensive AI countermeasure",
"text_overlay": "Persistent banner naming the prompt/hack"
},
{
"slot": "Tool Setup",
"visual": "Same framing, speaker uses hand gestures to clarify prerequisites",
"seconds": 18.5,
"voiceover": "Specify necessary client apps for local execution",
"text_overlay": "Animated synced captions"
},
{
"slot": "Prompt Dictation",
"visual": "Speaker slows delivery, dictating exact instructions clearly",
"seconds": 34.5,
"voiceover": "Dictate exact audit prompt verbatim",
"text_overlay": "Highlighted captions tracking every dictated word"
},
{
"slot": "Social Proof & Sign-off",
"visual": "Speaker nods, leans back slightly, casual sign-off",
"seconds": 20.7,
"voiceover": "Describe shocked beta user reactions and urge viewer to run it",
"text_overlay": "Synced captions ending with final CTA"
}
],
"what_can_change": [
"Target threat topic (finance, privacy, SEO)",
"Specific AI desktop tool referenced",
"Speaker appearance and location"
],
"template_summary": "One-take talking-head addressing a viral fear, explaining how to flip the tool defensively, and dictating a precise prompt.",
"what_must_be_kept": [
"Continuous uncut direct-to-camera presentation",
"Persistent top banner with clear utility hook",
"Slow, copyable dictation of the exact prompt",
"Word-by-word synced caption highlighting"
],
"generation_prompts": [
{
"prompt": "Vertical 9:16 smartphone video close-up of a 40-year-old tech creator with glasses and beard speaking candidly to camera in home interior, natural daylight, single continuous take.",
"shot_index": 1,
"negative_prompt": "cinematic camera cuts, b-roll, background music, studio backdrop, oversaturated"
}
]
},
"props_apps_and_products": [
{
"name": "Claude Desktop",
"how_used": "Mentioned as compatible AI client",
"first_seen": "00:24.0"
},
{
"name": "ChatGPT Desktop",
"how_used": "Mentioned as compatible AI client",
"first_seen": "00:25.0"
}
]
}model gemini-3.8-flash · analyzed from the actual video and audio · 2026-10-28 · timestamps are estimates
Caption
Scan yourself before hackers do. #aihack #cybersecurity #aisafety #ai #artificialintelligence
Is this your account? Ask us to remove @nate.b.jones: we stop tracking it and delete what we hold about it within a month.
Get this for your own niche
Copy AI founders for free, scan it on your plan, and get teardowns and adaptations for every outlier.
More outliers in AI founders
Full report- 200×1.0M vs 4.9k base@ai.with.andrew69k followers14d ago
Claude is offering you a free subscription for one year.
tutorialutilityvideo analyzed · 48seng 1.2× · 38k saves · 13k shares - 48×267k vs 5.6k base@20vc_tok280k followers4d ago
FRANCE WANTS TO TAX YOUR INTERNET USAGE
talking-headrelatable painvideo analyzed · 75seng 2.0× · 1.4k saves · 2.8k shares - 17×236k vs 5.0k base@bengusberg82k followers11d ago
The rumors are true. Google can now tell you used AI in your writing with 93% accuracy,
talking-headrelatable painvideo analyzed · 76seng 1.0× · 12k saves · 2.3k shares - 16×228k vs 5.0k base@bengusberg82k followers8d agotalking-headutilityvideo analyzed · 60seng 1.2× · 14k saves · 3.2k shares
- 14×60k vs 4.2k base@evisdrenova52k followers10d ago
#greenscreen #ai #anthropic #claude #tech
videoeng 3.2× · 644 saves · 256 shares