Topic

security

3 min read

Testing the Permission Matrix

A matrix that only proves the admin can do everything has not really been tested.

Read article
2 min read

Redact Before You Paste It Into the Coding Agent

The prompt is not a scratchpad. A token, an internal hostname, or customer PII you paste into the agent lives in a log you do not fully control, long after the fix ships.

Read article
2 min read

The agent cached a GET by path and handed one tenant another tenant's row

The agent memoized a slow GET endpoint keyed only on the request path, warmed it locally under one fixed test user, and stayed green. In staging, a second tenant read the first tenant's row because the cache key never included the authenticated subject.

Read article
2 min read

Your MCP Hub Exposes Every Tool to Every Agent. That's the Bug.

A shared MCP hub that lists all 40 tools to every connected agent is a convenience until the billing agent starts calling create_user. The fix isn't stricter prompts — it's a smaller tool list per agent, derived from the spec.

Read article
4 min read

Scope MCP Keys to the Human, Not to the Team

When you hand MCP gateway access to support and PMs, a team-wide key becomes the incident waiting to happen. Scope the key to the human, the role, and the three ops they actually use.

Read article