feat: add redact/warn prompt modes - #44
Merged
Merged
Conversation
UserPromptSubmit hooks can't rewrite the submitted prompt, only block it or allow it with an added message, so a new "mode" config option (block | redact | warn) picks between the current hard-block behavior, a block whose reason includes a copy-pasteable redacted prompt, and a non-blocking systemMessage warning.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
modeconfig option ("block" | "redact" | "warn", default"block") so a detected prompt can be blocked, blocked-with-a-copy-pasteable-redacted-version, or allowed through with a non-blocking warning.redactstill blocks the original prompt - confirmed that Claude Code'sUserPromptSubmithook API has no way to rewrite/replace a submitted prompt - but the block reason includes a cleaned copy you can paste back in instead of manually retyping around the sensitive parts.warnlets the prompt through unmodified and surfaces a non-blockingsystemMessagelisting what was found.src/hook/response.tsmodule.modevalues fall back to"block"with a console warning.Closes #12
Test plan
npm run buildnpm test- 347 tests pass, including newtests/hook-response.test.tsandtests/config-mode.test.tsnpm run lintscripts/prompt-guard.jsagainst a sample prompt for all three modes and confirmed the JSON output/exit behavior for each