PulseAugur
EN
LIVE 07:35:22

Perplexity unveils new AI security tools and sandbox platform

By PulseAugur Editorial · [7 sources] ·

Perplexity has launched several new security initiatives and tools aimed at enhancing the safety and trustworthiness of AI agents. These include Bumblebee, a scanner for risky packages on developer machines, and Numbat, an agent-detection and response layer. The company also detailed its SPACE sandbox platform, which isolates AI tasks, and its Portable Computer system that runs models locally. Perplexity has conducted rigorous testing, including giving AI models root access within a sandbox environment, with no escapes observed. AI

IMPACT Enhances trust and security in AI agents, potentially accelerating enterprise adoption of AI tools.

RANK_REASON Multiple product launches and security feature announcements from a single company.

Read on X — Perplexity →

AI-generated summary · Google Gemini · from 7 sources. How we write summaries →

Perplexity unveils new AI security tools and sandbox platform

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Multiple product launches and security feature announcements from a single company.
Source corroboration
7 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
8 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [7]

  1. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Our Secure Intelligence Institute works with researchers at Stanford, CMU, Duke, Columbia, Ohio State, and UVA.

    Our Secure Intelligence Institute works with researchers at Stanford, CMU, Duke, Columbia, Ohio State, and UVA. We’re also working with NVIDIA and the Open Secure AI Alliance, and sharing tools and findings so others can strengthen their own systems. https://t.co/Ss44JdZb5T

  2. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Bumblebee checks developer machines for risky packages and extensions.

    Bumblebee checks developer machines for risky packages and extensions. Computer reviews findings from Bumblebee and Numbat and proposes better detection rules. Humans approve every change before it ships. Agents help improve the controls but can't approve their own changes.

  3. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Numbat independently monitors coding agents across thousands of our endpoints.

    Numbat independently monitors coding agents across thousands of our endpoints. It works across Claude Code, Codex, OpenCode, and Pi. It can block dangerous actions before they run and detect sequences such as reading a secret, then sending data out.

  4. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Portable Computer keeps the model and harness on your device.

    Portable Computer keeps the model and harness on your device. Deterministic code enforces policy, and approved actions run in an always-on OS sandbox that restricts processes, files, and network access. If the sandbox is unavailable, tools don’t run.

  5. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    In Comet and Computer, BrowseSafe screens retrieved content for prompt injection security. Tool guardrails reinforce your intent, and sensitive actions require

    In Comet and Computer, BrowseSafe screens retrieved content for prompt injection security. Tool guardrails reinforce your intent, and sensitive actions require confirmation. Trail of Bits audited these defenses. Enterprise audit logs record all agent actions.

  6. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    We test those boundaries. We gave 9 models root access inside SPACE. None escaped the VM in 108 runs.

    We test those boundaries. We gave 9 models root access inside SPACE. None escaped the VM in 108 runs. Separate network tests exposed bypasses we fixed and retested. We also disclosed network-policy weaknesses in 8 of 10 other platforms to their vendors.

  7. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    SPACE runs every Computer task in an isolated microVM, with platform credentials and network controls outside the sandbox.

    SPACE runs every Computer task in an isolated microVM, with platform credentials and network controls outside the sandbox. Snapshots let us roll back changes. Enterprise customers can revoke encryption keys to make protected data unreadable; the agent can’t override it.

RELATED ENTITIES

RELATED TOPICS