+Intertrace Insights
Newss
The incidents and disclosures behind the headlines, and what they change for teams running agents.
- Pieces
- 57
- Threat research
- 16
- Updated
- Oct 20, 2026
5 pieces · newest first
News9 min read
When agents delegate to agents: what A2A verifies, and what your chain still has to
The Agent2Agent specification makes card signing optional and leaves authorization to each implementer, and public research shows a remote agent steering a client agent into an unauthorized trade. The questions to ask before your agents accept work from other agents, answered from the spec.
Intertrace Threat Research
News9 min read
EchoLeak and the exfiltration channel in your assistant's renderer
CVE-2025-32711 let one crafted email pull data out of Microsoft 365 Copilot through an image the client fetched on its own. A step-by-step teardown of the four defenses it got past, and why the fix that transfers is inspecting what leaves.
Intertrace Threat Research
News10 min read
The MCP supply chain is your package supply chain, with your agent's keys attached
Most MCP servers arrive as a README line that downloads and runs the newest package on every launch. Eight checks for the code your agents run, each tied to a public 2025 failure, with the reason it matters and the test that proves it.
Intertrace Threat Research
News9 min read
Indirect prompt injection is now an operations problem
Assistants that read email, tickets, web pages and shared documents give every outside author a way to talk to them. Why indirect prompt injection will not be patched away, the strongest objection to that view, and what running it as an operational risk takes.
Intertrace Threat Research
News9 min read
August 2, 2026: what the EU AI Act now asks of agent deployers, and what NIST has started
The EU AI Act's general application date arrived days after the Digital Omnibus moved high-risk obligations to December 2027 and August 2028. Six decisions an agent deployer has to make now, in order, and where NIST's agent work stands.
Intertrace Threat Research
+Stay current
New research, the week it publishes.
Subscribe with RSS, or email support@intertrace.ai with a topic you want covered. To see the controls in action, try the Simulation Lab or read the documentation.