Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.110 Home All releases olderv2.1.109 v2.1.111newer
Claude Code v2.1.110

Hook Security Enhancement

When a hook rewrites the user's input, permissions are now re-validated against the modified input. This prevents hooks from bypassing permission checks by rewriting a denied command into something different.

Evidence

Permission re-validation (search for "ask rule on hook-rewritten input")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.110 →