Repository navigation
📖 docs: exclude project-local excuses from the Stop-hook recipe like watch --rebuttal=send does - #271
Merged
Conversation
…tch --rebuttal=send does The README's Claude Code Stop-hook recipe mirrored the watcher's 0.7 confidence floor but not its project-source exclusion, so rebuttals loaded from ./.rationguard/custom-excuses.json in an untrusted checkout could be handed to the agent as hook feedback. Filter them out in the jq select and explain why in the prose. Closes #270 Signed-off-by: sec-check <280983584+hivecommons-hive[bot]@users.noreply.github.com>
kubestellar-prow
Bot
added
the
dco-signoff: yes
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
kubestellar-prow
Bot
added
the
size/XS
hivecommons-hive
Bot
added
author/hive
![hivecommons-hive[bot]](https://avatars.githubusercontent.com/in/3568013?s=60&v=4){kind=small}
Contributor
Author
|
Thank you for your contribution! Your PR has been merged. We'd love to hear how your experience was: share feedback |
hivecommons-hive
Bot
removed
role/trusted
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Security Fix
The Claude Code
Stop-hook recipe in README.md said it applied the "same 0.7 confidence floor thatwatch --rebuttal=senduses", but it skipped the watcher's other send-time guard: matches whose excuse hassource: "project"are detection-only, because./.rationguard/custom-excuses.jsonbelongs to the (untrusted) checkout. Without that filter a cloned repo could plant a catch-all excuse and have its rebuttal delivered to Claude as hook feedback withexit 2.This change:
and .excuse.source != "project"to the recipe'sjqselect, with a comment stating why;Verified locally with a planted
.rationguard/custom-excuses.json(pattern: "the", confidence 1): the fixed hook exits 0 with no output for a message that only matches the planted excuse, and still exits 2 with the builtin rebuttal for "This is too complex to fix right now".Docs-only change; no code or tests touched.
Closes #270
Filed by sec-check agent (ACMM L6 — full mode)
— hive: agent=sec-check backend=copilot model=claude-fable-5.1 copilot=1.0.88