Invariant Labs
Security testing and analysis for AI agents; acquired by Snyk
Invariant Labs, an ETH Zurich spin-off, built tools for testing, tracing, and securing AI agents, discovering attack classes like MCP tool poisoning and rug pulls. It was acquired by Snyk in June 2025 to anchor Snyk's agentic AI security research.
Coined 'tool poisoning' and 'MCP rug pull' attacks
| Website | invariantlabs.ai |
|---|---|
| Domains | Cybersecurity, Alignment |
| Location | Zurich |
| Team size | 1-10 |
| Founded | 2024 |
| Funding | Acquired by Snyk (June 2025) |
| Raising | No |
| Founders | Marc Fischer, Luca Beurer-Kellner |
Similar startups
Also listed under Cybersecurity, Alignment.
| Name | Domains | Location | Team | Funding | Raising |
|---|---|---|---|---|---|
| Rise Data Labs US-based expert human data and custom RL environments for enterprise AI | Computer Use, Coding, Finance, Cybersecurity, Legal, Data Labeling, Enterprise, Multi-Domain, RLHF, Custom Environments | United States | - | - | Yes |
| Andon Labs Long-horizon autonomy benchmarks like Vending-Bench | Long Horizon, Alignment | San Francisco | 1-10 | Seed (Y Combinator) | - |
| ARIMLABS Security and long-horizon environments for agentic AI | Cybersecurity, Long Horizon | Warsaw | 11-25 | - | - |
| dmodel Alignment-oriented environments focused on reward quality | Machine Learning, Alignment | San Francisco | 11-25 | - | - |
| Gray Swan AI Adversarial red-teaming arenas and safety evals for frontier models | Cybersecurity, Alignment | Pittsburgh | 11-25 | ~$40M (reported) | - |
| Incalmo Offensive-security environments for AI agents | Cybersecurity | San Mateo | 11-25 | - | - |