🛡️ Sentinel: [MEDIUM] Fix Error Message Leakage in JSON-RPC Responses

[davidruzicka]

🚨 Severity: MEDIUM
💡 Vulnerability: Unsanitized error messages were directly returned in JSON-RPC API responses for prompts/get, resources/read, and completion/complete methods, potentially leaking sensitive configuration paths or tokens via Error.message on the client-side.
🎯 Impact: If a backend operation crashed due to a bad configuration or token issue, the raw exception trace/message could be sent to the user, bypassing our secure error formatting.
🔧 Fix: Updated the catch blocks in these three JSON-RPC methods to correctly use the internal generateCorrelationId() function and log the raw error context only on the backend server logs. The client-facing error message now leverages this.formatErrorForClient(error, correlationId) to scrub sensitive information.
✅ Verification: Ran the full test suite and updated mcp-server-apps.test.ts to expect generic validation strings instead of raw error dumps. Tests passed successfully.

---

PR created automatically by Jules for task 10783194581880560094 started by @davidruzicka

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ All tests successful. No failed tests found.

📢 Thoughts on this report? Let us know!