
Official updates for developers building with @1Password. Securely manage API keys, credentials, and agent access without exposing your secrets.
Joined April 2026
- Tweets630
- Following218
- Followers1.1K
- Likes597
Pinned Tweet
The FBI just issued a warning about AI agents being used to hack companies.
Some attacks reached privileged access in under 3 HOURS.
67,000 people's data exposed. 2,250+ downstream tenants affected in a separate campaign.
The tool behind it? ARTEX.
Here's how the attacks work. 🧵
1Password Developers retweeted
Classic attacks now have AI-agent versions:
Phishing → goal hijacking
Supply chain → tool poisoning
Credential theft → secrets in context
Persistence → memory poisoning
Attackers want the same things. The route is new.
Here are 7 to know & how to build your defense:
🧵(1/10)
1Password Developers retweeted
Five places to start:
1. Treat external content as untrusted
2. Give agents the minimum permissions they need
3. Keep credentials out of model context
4. Audit agent tools and dependencies
5. Monitor actions, not only prompts
🧵(9/10)
Classic attacks now have AI-agent versions:
Phishing → goal hijacking
Supply chain → tool poisoning
Credential theft → secrets in context
Persistence → memory poisoning
Attackers want the same things. The route is new.
Here are 7 to know & how to build your defense:
🧵(1/10)
Five places to start:
1. Treat external content as untrusted
2. Give agents the minimum permissions they need
3. Keep credentials out of model context
4. Audit agent tools and dependencies
5. Monitor actions, not only prompts
🧵(9/10)
We spent decades teaching people not to trust everything they read. Agents need the same lesson.
Which of these seven is hardest to defend in your stack today?
How we approach credentials for agents: 1password.dev
🧵(10/10)
1
24
1Password Developers retweeted
We'll all have to disconnect from the Internet, thanks to AI. Great job, AI developers. 😡
1Password Developers retweeted
The FBI just issued a warning about AI agents being used to hack companies.
Some attacks reached privileged access in under 3 HOURS.
67,000 people's data exposed. 2,250+ downstream tenants affected in a separate campaign.
The tool behind it? ARTEX.
Here's how the attacks work. 🧵
Only 31% of consumers say they're likely to trust AI agents to make decisions on its own. Better control helps close that gap. 🔐
If your agent needs a login, keep the password out of the prompt. You approve the request, and @1Password fills it in. The agent never sees it.
What’s the difference between AI chatbots and AI agents? As more and more companies release personal AI agents, there’s never been a better time to find out.
Read 1Password’s latest blog for an overview on how agents work, and how you can use them safely: bit.ly/4feiauj
8
597
So how do developers defend against this?
• Scan code and CI/CD for exposed secrets
• Use short-lived, least-privilege credentials
• Enforce server-side API authorization
• Audit third-party and OAuth access
• Monitor unusual token and API activity
Speed matters. Detection matters more.
The biggest shift isn't AI inventing new vulnerabilities.
It's AI finding and chaining existing weaknesses faster than defenders can respond.
Attacks that once required extensive manual effort can increasingly be automated.
Full FBI advisory:
ic3.gov/CSA/2026/261113.pdf





