Son Dakika
ESTorero Tomás Angulo, muy grave tras ser cogido por un toro en MoralzarzalESCertificado de Bankia a Dubái: la clave para la offshore de ZapateroESCandidato presidencial colombiano habla sobre apoyo de Trump y relación con EspañaESYohir Akerman, el "espía colombiano" que opera en la sombra de la política españolaESPedri, el debate sobre su posición ideal en la Selección EspañolaESLa SGAE se reinventa: de la crisis reputacional al récord de recaudaciónESJulio Borges: "Sabemos desde hace 10 años que Zapatero era lobista, pero nadie nos creía"ESFeijóo siembra dudas sobre el futuro de Juanfran Pérez Llorca al frente del PP valencianoESSpain's Strategic Investment Committee: A Delayed and Controversial InitiativeESCathie Wood: SpaceX es 'la compañía' y la IA es una oportunidad de 22.500 millonesESTorero Tomás Angulo, muy grave tras ser cogido por un toro en MoralzarzalESCertificado de Bankia a Dubái: la clave para la offshore de ZapateroESCandidato presidencial colombiano habla sobre apoyo de Trump y relación con EspañaESYohir Akerman, el "espía colombiano" que opera en la sombra de la política españolaESPedri, el debate sobre su posición ideal en la Selección EspañolaESLa SGAE se reinventa: de la crisis reputacional al récord de recaudaciónESJulio Borges: "Sabemos desde hace 10 años que Zapatero era lobista, pero nadie nos creía"ESFeijóo siembra dudas sobre el futuro de Juanfran Pérez Llorca al frente del PP valencianoESSpain's Strategic Investment Committee: A Delayed and Controversial InitiativeESCathie Wood: SpaceX es 'la compañía' y la IA es una oportunidad de 22.500 millones
Newsgather
GeriPerplexity Open-Sources Bumblebee Security Tool
Perplexity Open-Sources Bumblebee Security Tool
Gelişiyor
Decrypt25.05.2026Teknoloji2 dk okuma

Perplexity Open-Sources Bumblebee Security Tool

Hızlı Bakış

  • Perplexity has open-sourced Bumblebee, a security tool that scans developer computers for malicious software, extensions, and AI tool configurations without running code.
  • It analyzes metadata to detect threats, including recent supply-chain attacks like the one by TeamPCP.

Yapay zekâ özeti

Neden Önemli?

Traditional security scanners work by running code, similar to testing food by eating it. Perplexity's new open-sourced tool, Bumblebee, takes a 'read-only' approach, analyzing code and configurations without execution to detect threats.

Yazı boyutu

Imagine you suspect someone poisoned a bottle of water in your house. To check, you drink from every bottle. That's roughly how most security scanners work.

Perplexity just open-sourced a tool called Bumblebee that takes a different approach. It scans developer computers for infected software packages, malicious browser extensions, and compromised AI tool configs—without ever running the code it finds. It reads the code, the ingredient label instead of eating the food.

On May 11, a hacker group called TeamPCP slipped malicious code into over 160 software packages used by millions of developers worldwide—including packages from Mistral AI, UiPath, and a widely used React tool with 12 million weekly downloads. The attack spread automatically the moment developers installed those packages. Perplexity’s Bumblebee could have prevented that, the company says.

Why "read-only" is the whole point

Software packages—especially in the JavaScript world—can run hidden scripts the moment you install them. That's exactly how the May 11 attack spread so fast. The malicious code fired automatically on install, before anyone noticed anything was wrong.

A scanner that invokes the package manager to check for infections can trigger those same scripts. You go looking for the worm; the worm runs. Bumblebee sidesteps this by never calling any package manager at all. It reads raw metadata files—the records that describe what's installed—without touching the software itself.

The genuinely new piece is that Bumblebee also scans MCP configuration files—the local files that tell AI assistants like Claude or Cursor which external services they're allowed to connect to.

MCP connectors give AI tools access to emails, databases, calendars, and code. If an attacker sneaks a malicious connector into that config, your AI assistant could leak credentials or run unauthorized commands in the background. Most security tools aren't checking for this yet.

Beyond MCP, it covers browser extensions on Chrome, Edge, Brave, Arc, and Firefox, plus editor plugins in VS Code and its forks. The whole scan happens in one pass, outputs a clean structured list of what it found, and never modifies anything on the machine.

How Perplexity uses it internally

Perplexity has been running Bumblebee internally to protect the systems behind its search product, its Comet browser, and its Computer AI agent. When a new threat surfaces, Perplexity Computer drafts a catalog entry for it, a human reviews and approves it, and Bumblebee runs across all developer machines to check for matches.

Teams can run their own catalogs the same way. The tool ships with a built-in threat directory seeded from recent supply-chain attacks, including the May 11 campaign. The group behind that attack—tracked by Google under the alias UNC6780—has been running coordinated software poisoning campaigns since at least March 2026.

Bundan Sonra Ne Olabilir?

Yapay zekâ öngörüsü — kesinlik taşımaz

  • Bumblebee will see adoption by development teams seeking enhanced security.

    Muhtemel · Aylar içinde

  • Other security tools may begin to incorporate 'read-only' scanning methods.

    Olası · Uzun vadede

Açık Sorular

  • What is the specific impact of the TeamPCP attack on developers who installed the malicious packages?
  • How widely adopted is Bumblebee expected to be among developers?
  • What are the limitations of Bumblebee's 'read-only' scanning approach?
  • Will other security companies adopt similar 'read-only' methodologies?

İlgili Konular

Bu haber ilk olarak şurada yayınlandı: Decrypt.

İlgili Haberler

ChatGPT Users Suspect OpenAI is A/B Testing GPT-5.6
Gelişiyor·1 g önce

ChatGPT Users Suspect OpenAI is A/B Testing GPT-5.6

ChatGPT users are reporting significant slowdowns and performance differences, leading to speculation that OpenAI is secretly A/B testing a new GPT-5.6 model. Developers are sharing screenshots and videos comparing generation times, with some tests showing much longer durations than the current GPT-5.5 Pro. Leaked details suggest improvements in reasoning and design generation, with a potential release date in late June.

Decrypt
Bu konuda daha fazlaperplexity