@InvariantLabsAI profile picture
Invariant Labs @InvariantLabsAI

Invariant Labs makes AI Agents secure and reliable.

Joined July 2024
  • Tweets 117
  • Following 28
  • Followers 645
50 Photos and videos
We’re thrilled to officially join forces with @snyksec! Together, we’re changing the landscape of the agentic AI future. More to come!
1
2
10
1,686
Announcement: snyk.io/news/snyk-acquires-i…

Snyk Acquires Invariant Labs to Accelerate Agentic AI Security Innovation | Snyk

Acquisition Deepens Snyk Labs Research Bench, Advances Real-Time Defense for Emerging Threats, Extends Security Capabilities in a Single AI-Trust Platform

snyk.io
490
Invariant Labs retweeted
Luca Beurer-Kellner@lbeurerkellner
26 May 2025
😈 BEWARE: Claude 4 GitHub MCP will leak your private GitHub repositories, no questions asked. We discovered a new attack on agents using GitHub’s official MCP server, which can be exploited by attackers to access your private repositories. creds to @marco_milanta (1/n) 👇
46
474
2,158
503,295
Invariant Labs@InvariantLabsAI
26 May 2025
Invariant researchers have uncovered a new security flaw in GitHub’s official MCP server, enabling attackers to exfiltrate private repository data. The toxic flow was identified during an automated scan using Invariant's security stack. Learn more: invariantlabs.ai/blog/mcp-gi…

GitHub MCP Exploited: Accessing private repositories via MCP

We showcase a critical vulnerability with the official GitHub MCP server, allowing attackers to access private repository data. The vulnerability is among the first discovered by Invariant's security...

invariantlabs.ai
1
6
541
Invariant Labs@InvariantLabsAI
22 May 2025
🔵 New release: Invariant MCP-scan v0.2 is here! Track, audit & secure all local MCP traffic with static dynamic scanning, local guardrails, and customizable policies. Ideal for orgs prioritizing agent security & compliance. Docs: explorer.invariantlabs.ai/do… #AI #DevSecOps
3
384
Invariant Labs@InvariantLabsAI
29 Apr 2025
We are proud to share that AgentDojo, an Invariant research project done with @ETH, has won the first price of the @cais SafeBench competition. We truly appreciate this recognition from the community. Learn More: invariantlabs.ai/blog/agentd…

Invariant Research wins first prize of Center for AI Safety competition

AgentDojo wins $50,000 prize in the SafeBench competition, hosted by the prestigious Center for AI Safety.

invariantlabs.ai
11
2,538
🛡️ We are thrilled to partner with @SmitheryDotAi to protect their MCP servers with Invariant MCP-scan. Also, a lot of features will be dropping in MCP-scan soon!
3
2
5
1,306
Blog post: invariantlabs.ai/blog/smithe…

Announcing our partnership with Smithery

Invariant MCP-Scan is now protecting Smithery

invariantlabs.ai
1
1
287
MCP-scan: github.com/invariantlabs-ai/…

GitHub - snyk/agent-scan: Security scanner for AI agents, MCP servers and agent skills.

Security scanner for AI agents, MCP servers and agent skills. - snyk/agent-scan

github.com
1
2
238
Invariant Labs retweeted
Bill Doerrfeld@DoerrfeldBill
24 Apr 2025
MCP is the hottest thing in AI right now, but people aren't really talking about the security implications... I covered a recently discovered exploit and mitigations on the @thenewstack today: thenewstack.io/building-with…

Building With MCP? Mind the Security Gaps

A recent exploit raises concerns about the Model Context Protocol, AI's new integration layer.

thenewstack.io
1
3
9
1,588
Invariant Labs retweeted
Marc Fischer@marc_r_fischer
24 Apr 2025
We recently shipped a lot of updates to mcp-scan: - whitelisting of tools - Improvements to the server (reducing false-positives, improving detection) - run via npm/npx Much more coming soon! github.com/invariantlabs-ai/… #mcp

GitHub - snyk/agent-scan: Security scanner for AI agents, MCP servers and agent skills.

Security scanner for AI agents, MCP servers and agent skills. - snyk/agent-scan

github.com
2
11
925
🛡️ We just released Invariant Guardrails — a contextual guardrail system for agents and MCP-powered AI applications. Open source & easy to deploy. 🧵
2
3
361
more replies
Invariant Guardrails, Gateway, and Explorer are all open-source. github.com/invariantlabs-ai/… Check them out! We would love some feedback.

GitHub - invariantlabs-ai/invariant: Guardrails for secure and robust agent development

Guardrails for secure and robust agent development - invariantlabs-ai/invariant

github.com
1
1
190
For more details on Invariant Guardrails, check out our blog post: invariantlabs.ai/blog/guardr…

Introducing Guardrails: The contextual security layer for the agentic era

We are releasing Invariant Guardrails, our state-of-the-art contextual guardrailing system for AI applications. It supports tool calling, MCP as well as data flow control and contextual constraints.

invariantlabs.ai
1
146
Invariant Labs retweeted
Luca Beurer-Kellner@lbeurerkellner
15 Apr 2025
🔴🌎 New MCP attack on BrowserMCP We show an MCP attack on the popular BrowserMCP. It allows attackers to read arbitrary files from your machine, when the agent visits the website below. Try yourself with: access.invariantlabs.ai No bad MCP server needed. (1/n)👇
4
13
96
31,309
After covering MCP vulnerabilities over the last few days, today, we are launching MCP-scan, a security scanner to detect MCP attacks. Run it now: uvx mcp-scan@latest 🧵
1
3
12
1,062
more replies
For more details, check out our full blog post on MCP-Scan: invariantlabs.ai/blog/introd…

Introducing MCP-Scan: Protecting MCP with Invariant

Today we are launching MCP-Scan, a security scanner designed to protect your agentic systems from MCP-based security vulnerabilities, including Tool Poisoning Attacks and MCP Rug Pulls.

invariantlabs.ai
1
4
202
A small disclaimer: We use Invariant Guardrails server-side via an API, and we are collecting tool names and descriptions for security research purposes (not your user data!). Don't use it if you don't want to share your tools.
4
157
Load more