The abilities we deliberately left out
Most of the pitch is about what you can switch on. This post is about the floor under all of it: what an agent cannot do here, no matter what you enable.
Read moreGovernance
18 posts in Governance.
What we fixed in the 1.7.1 correctness release
A fix-only release: WPML sweeps now read every configured language, tool discovery matches permission, and a broken discovery route resolves again.
Read moreWhat 1.7.0 adds: Enable all writes, and a fuller audit log
Version 1.7.0 adds a one-click way to enable a section's ordinary writes, deliberately leaving deletes and high-risk abilities locked, plus a fuller audit log.
Read moreWhat we fixed in the 1.7.0 correctness release
Version 1.7.0 closes an OAuth revocation race, stops a payment gateway credential leak, and fixes four ACF writes that were destroying content.
Read moreWhat we fixed: setting alt text said permission denied, for everyone
In 1.7.0 an agent asked to set an image's alt text hit a bare permission denied and had no way to know a different tool would have worked. Here is why, and what changed.
Read moreAI agent WordPress security risks
Five real risks of an AI agent on WordPress, deletion, data leakage, injected content, and credential exposure, mapped to the control that limits each one.
Read moreWordPress AI prompt injection, contained
A hidden instruction in a comment can fool an AI agent on WordPress. What indirect prompt injection is, and how governance contains it when detection can't.
Read moreA WordPress AI audit log you can trust
Three 1.6.2 fixes make the plugin's audit log worth trusting: it records the true cause of a block, covers every path that changes state, and stays readable.
Read moreGuard WooCommerce customer data from AI agents
Managing a store and editing a user are different powers. Here is why customer data belongs behind the capability that actually governs editing user accounts.
Read moreWe said the audit log stored nothing. That was not quite true.
In 1.6.2 we corrected a claim about the audit log. It keeps identifier-only values by design, never free-text content, and here is why that line matters.
Read moreWhat we fixed in the 1.6.2 hardening release
Version 1.6.2 corrects a claim about our own audit log, tightens who can edit customer data, and closes gaps in what the plugin records and sanitizes.
Read moreHigh-risk lock and read-only mode, explained
Two controls decide what an AI agent is even offered on your WordPress site, before any per-call permission check runs: the high-risk lock and read-only mode.
Read moreWhat we fixed in the 1.4.1 standards release
A user-reported OAuth bug and six related fixes bring error responses, discovery, and tool status codes in line with what MCP and OAuth clients expect.
Read moreWhat we fixed: media reads reached past the uploader
In 1.4.3 an author-level user could read the entire WordPress media library, not just their own uploads. Here is the bug, the fix, and what else shipped.
Read moreWhat we fixed when a draft post went live
In 1.4.2 we fixed a bug where asking for a draft post published it live, two related permission gaps, and two WooCommerce order and product update bugs.
Read moreReliable agent tools: contract tests and verified writes
How contract tests against real vendor code and write verification keep an AI agent's WordPress tools honest and trustworthy.
Read moreWhat we fixed in the 1.3.0 security release
In 1.3.0 we turned OAuth off by default and fixed real security gaps in our own plugin, patched in the open. Here is what changed.
Read moreOff by default: how the governance model works
A walk through the governance model behind Agent Abilities for MCP, covering least privilege, off by default, capability gating, and an honest audit log.
Read more