🔒 Security: Critical Prompt Injection in Claude Code GitHub Action#39
Merged
AmberLJC merged 1 commit intoOrchestra-Research:mainfrom Mar 20, 2026
Conversation
The `claude.yml` workflow triggers on any issue comment, pull request review comment, or issue creation containing the text `@claude`. It then runs the `anthropics/claude-code-action` with elevated repository permissions (`contents: write`, `pull-requests: write`, `issues: write`). Because there is no authorization check to verify who created the comment or issue, any external user (even unauthenticated to the organization) can open an issue on the public repository and instruct the Claude agent to execute arbitrary code, modify repository contents, push malicious commits to the default branch, or exfiltrate secrets (like `CLAUDE_CODE_OAUTH_TOKEN`). This allows complete compromise of the repository. Affected files: claude.yml
Collaborator
|
Good catch! Thanks @tang-vu |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #38
🔒 Security Fix
Problem
The
claude.ymlworkflow triggers on any issue comment, pull request review comment, or issue creation containing the text@claude. It then runs theanthropics/claude-code-actionwith elevated repository permissions (contents: write,pull-requests: write,issues: write).Because there is no authorization check to verify who created the comment or issue, any external user (even unauthenticated to the organization) can open an issue on the public repository and instruct the Claude agent to execute arbitrary code, modify repository contents, push malicious commits to the default branch, or exfiltrate secrets (like
CLAUDE_CODE_OAUTH_TOKEN). This allows complete compromise of the repository.Severity:
criticalFile:
.github/workflows/claude.ymlSolution
The
claude.ymlworkflow triggers on any issue comment, pull request review comment, or issue creation containing the text@claude. It then runs theanthropics/claude-code-actionwith elevated repository permissions (contents: write,pull-requests: write,issues: write).Because there is no authorization check to verify who created the comment or issue, any external user (even unauthenticated to the organization) can open an issue on the public repository and instruct the Claude agent to execute arbitrary code, modify repository contents, push malicious commits to the default branch, or exfiltrate secrets (like
CLAUDE_CODE_OAUTH_TOKEN). This allows complete compromise of the repository.Changes
.github/workflows/claude.yml(modified)Testing
🤖 About this PR
This pull request was generated by ContribAI, an AI agent
that helps improve open source projects. The change was:
If you have questions or feedback about this PR, please comment below.
We appreciate your time reviewing this contribution!