Governance & privacy7 MIN READ
Permission-aware retrieval: the control most RAG diagrams omit
A retrieval system should establish the active principal and filter authorised resources before similarity ranking or model context assembly.
THE SOFTLANDER BLOG
Identity and access
Identity, credentials, authorisation and delegated authority for agents.
In Identity and access
13 articlesAgent security6 MIN READ
Designing credentials that expire before trust does
Agent credentials should be shorter-lived than the assumptions that justify them. Bind them to a workload, audience, task and action, then prove renewal and revocation work.
Agent security6 MIN READ
What least privilege means for an AI agent
Least privilege for agents is not a smaller role assigned once. It is authority narrowed by identity, task, resource, action, time and consequence at every tool call.
Security engineering6 MIN READ
Authorisation, not authentication, is where API breaches begin
Most APIs authenticate well and authorise badly. The defects that matter are object-level and function-level access rules scattered across handlers, where no single reviewer can see the whole rule.
Agent security6 MIN READ
Agent protocols are creating a new control surface
Protocols make tools and agents interoperable, but they also standardise discovery, delegation and context exchange. Those interfaces need explicit trust and policy controls.
Governance & privacy6 MIN READ
How to collaborate when client data cannot leave the environment
Keep sensitive data under client control by moving approved methods and people to the environment, exporting only the minimum reviewed evidence needed for collaboration.
Agent security6 MIN READ
A practical security review for an MCP server
Review an MCP server as a privileged protocol adapter: verify tool semantics, OAuth boundaries, token audience, downstream delegation, input handling, isolation, logging and consent.
Agent security6 MIN READ
How to map an AI agent’s attack surface
A useful agent threat model follows data, instructions, identity, tools and state across trust boundaries. This method turns the map into test cases and control decisions.
Governance & privacy6 MIN READ
Authority boundaries for procurement agents
A procurement agent may discover, compare and prepare, but supplier commitments require explicit mandates, separation and evidence.
Agent security6 MIN READ
Sandboxing and authorisation solve different problems
A sandbox limits what compromised execution can reach. Authorisation decides what an authenticated actor may do. Secure agents need both, tested independently and together.
Governance & privacy7 MIN READ
Data minimisation for agents that always want more context
Better agent context is not the largest possible context. It is the smallest authorised, relevant and timely data set that supports the task.
Agent security6 MIN READ
Can you trust an agent kill switch you have never tested?
Stopping one process may leave tools, queued actions, delegated agents and credentials active. Define the safe state, control every action path and rehearse the stop under load.
KEEP EXPLORING
Take the thinking
into your next discussion.
Read the method, assumptions and questions to ask.