Authority Provenance Must Survive Tool Calls
The final API sees a credential, but often loses the human request and delegation history that justified it.
AgentCollusionAI security startupNews
News and technical writing.
Company updates, technical analysis, and focused field notes on the trust layer for multi-agent systems.
Revocation Must Reach Long-Running Tasks
Cancelling a credential is not enough when agents have cached plans, artifacts, and delegated work already in motion.
Non-Repudiation Needs More Than a Signature
A signed action can prove origin and integrity without proving informed authority or a fair decision process.
Human-Present and Human-Absent Authority Differ
A user approving a final action creates different evidence from a standing intent executed later by agents.
MCP Token Passthrough Is Dangerous
Forwarding the client’s bearer token to an upstream API erases audience boundaries and creates confused deputies.
Resource Indicators Bound Agent Credentials
OAuth resource parameters help ensure a token issued for one tool cannot be replayed at another.
Tool Descriptions Are Part of the Attack Surface
Agents often choose tools from natural-language metadata that can redirect plans before any protected call occurs.
MCP Discovery Needs Issuer Validation
Discovering an authorization server is useful only if the client can prove it belongs to the intended protected resource.
MCP Deprecations Change Security Assumptions
When protocol features move or disappear, monitoring and authorization designs built around them can silently weaken.
Stateless MCP Moves State Into the Evidence Layer
Removing transport sessions improves scalability but forces systems to preserve task and principal continuity elsewhere.
