Who Does an AI Agent Represent?
How authority, incentives, accountability, and collusion risk change across B2B, B2C, and C2C transactions.
AgentCollusionAI security startupNews
News.
Product updates, research, and original films. Follow what we build and what we learn about systems of agents.
Threat Modeling the A2A Task Lifecycle
Why a valid task can still become unsafe as messages, artifacts, status updates, and counterparties accumulate.
Agent Card Caches Can Outlive Trust
Capability metadata changes slowly, but ownership, keys, endpoints, and risk can change immediately.
Signed Agent Cards Still Need Key Rotation
A valid signature proves integrity under a key; it does not prove that the key is current, independent, or correctly governed.
Agent Registries Will Become Ranking Systems
The registry that helps agents find one another also decides which providers receive visibility, work, and reputation.
Extended Agent Cards Need Selective Disclosure
More metadata can improve trust while simultaneously revealing internal capabilities, topology, and sensitive operations.
Push Notifications Add a Second Trust Channel
Asynchronous task updates can cross time, network, and credential boundaries that differ from the original request path.
A2A Extensions Need Governance, Not Just Names
Extensions preserve interoperability only when their semantics, ownership, and failure behavior remain understandable.
Version Negotiation Is a Security Boundary
Backward compatibility can preserve connectivity while removing the controls a newer relationship expected.
A2A and MCP Protect Different Boundaries
Agent interoperability and tool access solve different problems, so combining them does not create end-to-end trust automatically.