PulseAugur
EN
LIVE 11:43:16
Русский(RU) Perplexity Comet остался один на поле — и повторяет одну и ту же ошибку каждые два месяца

Perplexity Comet AI browser plagued by recurring security flaws

Perplexity Comet, an AI browser, has repeatedly demonstrated vulnerabilities where it fails to distinguish between user instructions and content on a webpage. These flaws, identified by various security firms including Trail of Bits and Brave, allow for the theft of sensitive information like emails and passwords. Despite multiple patches and security audits, new attack vectors continue to emerge, indicating a fundamental architectural issue. With the closure of its competitor Atlas Ai Model, Perplexity Comet is positioned as the primary AI browser, raising concerns about user trust and data security given its ongoing security challenges. AI

IMPACT Recurring security flaws in Perplexity Comet highlight the risks of AI browsers misinterpreting user instructions, potentially impacting user trust and data security.

RANK_REASON The article discusses ongoing security vulnerabilities and repeated failures in a specific AI-powered browser, Perplexity Comet, rather than a new model release or fundamental research.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Perplexity Comet AI browser plagued by recurring security flaws

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 Русский(RU) · Promptra Team ·

    Perplexity Comet is left alone on the field — and repeats the same mistake every two months

    <p>Atlas закрывается 9 августа, а по Comet с апреля 2025 по март 2026 вышли четыре независимых исследования и пять векторов атаки на письма и пароли — вот что стоит понять перед тем, как отдать браузеру свои сессии.</p> <p>Выстроенная подряд хронология читается как рабочий цикл: …