CometJacking prompt-injection in Perplexity's Comet AI browser
Security Tool/Service
Summary
Hide ▲
Show ▼
LayerX disclosed CometJacking, a prompt injection attack against Perplexity's Comet AI browser that uses a weaponized URL and the collection parameter to inject hidden instructions into the agent. In the reported scenario, a crafted link can steer the browser toward Gmail and Google Calendar data, Base64-encode it, and send it to an attacker-controlled endpoint, turning an ordinary click into a cross-service exfiltration path. Perplexity said the findings had "no security impact", but the issue shows how an agentic browser can be redirected by a link to access connected services without credential theft or direct user awareness.
Related Happenings
OpenAI ChatGPT renderer Markdown link/image phishing security flaw
Vulnerability
H score16
First: 29.05.2026 21:07
Last: 29.05.2026 21:07
Sources 1
About this happening:
ChatGPT has a response-renderer vulnerability that turns summarized third-party pages into live phishing links and auto-fetched attacker-hosted images inside the t...
OpenAI ChatGPT renderer Markdown link/image phishing security flaw
VulnerabilityAbout this happening: ChatGPT has a response-renderer vulnerability that turns summarized third-party pages into live phishing links and auto-fetched attacker-hosted images inside the t...
Perplexity Comet prompt-injection research shows agentic browsers can be trained into phishing traps
Technical Analysis
H score25
First: 11.03.2026 18:38
Last: 11.03.2026 18:38
Sources 1
How related:
Cybersecurity researchers have disclosed details of a new attack called CometJacking targeting Perplexity's agentic AI browser Comet by embedding malicious prompts within a seemingly innocuous link to siphon sensitive data, including from connected services, like email and calendar.
About this happening:
Perplexity's Comet AI browser is the focus of a technical analysis thread showing how prompt injection and malicious URLs can steer an agentic browser into data...
Perplexity Comet prompt-injection research shows agentic browsers can be trained into phishing traps
Technical AnalysisHow related: Cybersecurity researchers have disclosed details of a new attack called CometJacking targeting Perplexity's agentic AI browser Comet by embedding malicious prompts within a seemingly innocuous link to siphon sensitive data, including from connected services, like email and calendar.
About this happening: Perplexity's Comet AI browser is the focus of a technical analysis thread showing how prompt injection and malicious URLs can steer an agentic browser into data...
Fake AI assistant Chrome extension malware activity
Malware Activity
H score16
First: 16.02.2026 16:00
Last: 16.02.2026 16:00
Sources 1
About this happening:
A cluster of 30 malicious Chrome extensions posing as AI assistants is stealing email content and other sensitive data from Chrome users, creating a broad browser-...
Fake AI assistant Chrome extension malware activity
Malware ActivityAbout this happening: A cluster of 30 malicious Chrome extensions posing as AI assistants is stealing email content and other sensitive data from Chrome users, creating a broad browser-...
CL Suite Chrome extension stealing Meta Business data
Malware Activity
H score39
First: 13.02.2026 13:25
Last: 13.02.2026 13:25
Sources 1
About this happening:
The CL Suite Chrome extension is exfiltrating TOTP seeds, current 2FA codes, and Meta Business data from Meta Business Suite and Facebook Business Manager...
CL Suite Chrome extension stealing Meta Business data
Malware ActivityAbout this happening: The CL Suite Chrome extension is exfiltrating TOTP seeds, current 2FA codes, and Meta Business data from Meta Business Suite and Facebook Business Manager...
AiFrame malicious Chrome extension campaign
Campaign
H score40
First: 12.02.2026 15:41
Last: 12.02.2026 15:41
Sources 1
About this happening:
The AiFrame campaign uses fake AI assistants in the Chrome Web Store to distribute 30 malicious Chrome extensions that can steal email content, browser content,...
AiFrame malicious Chrome extension campaign
CampaignAbout this happening: The AiFrame campaign uses fake AI assistants in the Chrome Web Store to distribute 30 malicious Chrome extensions that can steal email content, browser content,...
Timeline
-
03.10.2025 17:01 3 articles · 9mo ago
LayerX discloses CometJacking in Perplexity's Comet AI browser
Initial DisclosureLayerX researchers disclosed CometJacking, a prompt-injection path in Perplexity's Comet AI browser that uses the URL collection parameter to inject hidden instructions, steer the agent toward connected services, and exfiltrate data such as Gmail messages and Google Calendar invites after encoding it in base64.
Show sources
- CommetJacking attack tricks Comet browser into stealing emails — www.bleepingcomputer.com — 03.10.2025 17:01
- CommetJacking attack tricks Comet browser into stealing emails — www.bleepingcomputer.com — 03.10.2025 17:01
- CometJacking: One Click Can Turn Perplexity’s Comet AI Browser Into a Data Thief — thehackernews.com — 04.10.2025 17:37