惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

P
Proofpoint News Feed
Blog — PlanetScale
Blog — PlanetScale
GbyAI
GbyAI
C
Check Point Blog
腾讯CDC
Stack Overflow Blog
Stack Overflow Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
The GitHub Blog
The GitHub Blog
A
About on SuperTechFans
Recent Announcements
Recent Announcements
L
LangChain Blog
Microsoft Azure Blog
Microsoft Azure Blog
小众软件
小众软件
J
Java Code Geeks
博客园_首页
Jina AI
Jina AI
美团技术团队
H
Help Net Security
MyScale Blog
MyScale Blog
Engineering at Meta
Engineering at Meta
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
人人都是产品经理
人人都是产品经理
Y
Y Combinator Blog
S
SegmentFault 最新的问题

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
Introducing Proton Pass for AI agents: The password manag...
Son Nguyen Kim · 2026-05-21 · via Hacker News - Newest: "AI"

AI agents can automate your most essential tasks, giving you an edge in the workplace or saving you time to do more of what really matters. But getting the maximum benefits often requires access to your private accounts, which is fraught with dangers.

To give you better control over your AI agent, Proton Pass now offers credential sharing via AI access tokens. Now you can easily give AI agents the credentials they need and nothing else, while monitoring their activity and staying organized. Every time an agent needs one of your credentials, it will have to give a reason, so you always know what your agent is doing and why.

Create access tokens from your Proton Pass settings and start deploying advanced AI automations in minutes. AI access tokens are now included at no extra cost on Pass Plus (included in Proton Unlimited), Pass Family, Pass Professional, and Proton Workspace — no expensive add-on required. You can now get the full benefits of agentic AI with reduced security risks while staying in complete control.

Learn how to use access tokens

Use your AI agent with confidence

Individuals and companies are deploying AI agents at breakneck speed. But the rollout has so far been uneven, inefficient, and unsafe. Most companies that have AI usage policies are violating them constantly. A survey from McKinsey(new window) found that while 62% of companies are experimenting with AI agents, only 23% are actually scaling AI agent usage. Why? In part because until now, it’s been difficult to give AI agents safe access to account credentials.

Most apps are still built for people, not AI agents that operate through APIs, Model Context Protocol (MCP) calls, and command-line tools. As a result, when an AI agent needs a credential, you might provide it in plaintext on an ad hoc basis or using complicated methods requiring specialized knowledge. Many people understandably just skip the AI agent altogether rather than take the risk, missing out on exponential efficiency gains.

Proton Pass for AI solves this problem by allowing you to share access in a convenient, auditable, and structured way — with a single prompt.

With Proton Pass, you can:

  • Segment and control access: Organize unique credentials for your agent inside dedicated vaults, sharing only what you need and nothing else.
  • Monitor credential usage activity: Every time your AI agent needs a credential, it leaves an audit log including a reason for access, so you can review and monitor every login.
  • Restrict and revoke access: Set an expiration for each access token and shut off access at any time.

Now it’s easier to stay organized when sharing multiple credentials with your agent, while keeping visibility and control over how they’re used.

Enable dozens of AI use cases, securely

AI access tokens are easy to set up. In your Proton Pass settings, create a new access token and copy and paste the setup instructions to your AI agent. Then simply ask your agent to perform actions that require access to the items you’ve shared with it.

Within minutes, you’ll be able to have your agent perform any number of time-saving tasks autonomously: Ask your agent to check your bank’s transaction history and categorize spending for the month, pull data from your fitness tracker and create a weekly wellness report, or ask your CRM to summarize the last three interactions with a specific client before a call with them.

Even if you’re not using an AI agent, you can also use access tokens in your own scripts and automatons, using the list of commands(new window) that Pass CLI accepts.

How Proton Pass protects your credentials

Proton Pass uses end-to-end encryption to secure your usernames, passwords, API keys, bank cards, and other items. Whatever you store in Proton Pass is only accessible to you, unless you choose to securely share it. AI access tokens are our newest secure sharing option to bring password management into the age of agentic AI.

Read-only vault access

Proton Pass vaults are encrypted digital containers for your items, such as logins, aliases, and credit card details. You can assign items to different vaults and then create access tokens specific to those vaults. AI agents only access the items they need and nothing else, and they won’t be able to create or edit items.

Manage vault access 2

For extra security, you can also set an expiration for each token, from one hour to one year, after which it can no longer be used.

Every access is logged and explained

Every time an AI agent uses an access token, this is logged and a reason for the access must be provided. These logs are easy to access, so you always know exactly what your AI agents are doing and why.

See exactly what your agent is doing. And why.

Learn how to use access tokens

Your agent does the work – you stay in control

Agentic AI can greatly amplify your personal productivity or improve your team’s workflows, but it’s vital that we harness its full power securely. Proton Pass lets you do just that, allowing you to embrace the efficiency of autonomous agents without surrendering control.

Whether you’re managing Jira tickets, analyzing energy usage, or researching papers, you can let your AI do the heavy lifting with greater peace of mind. Thanks to granular permissions, strict time limits, and full audit logs that explain every action, your sensitive data remains secure while your agent gets to work.