🛡️ Sentinel: [CRITICAL/HIGH] Fix raw exception information leakage#486
Closed
seonghobae wants to merge 3 commits into
Closed
🛡️ Sentinel: [CRITICAL/HIGH] Fix raw exception information leakage#486seonghobae wants to merge 3 commits into
seonghobae wants to merge 3 commits into
Conversation
|
👋 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 New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
…e-8632839196680902626
There was a problem hiding this comment.
Pull request overview
This PR hardens the Python analysis engine’s stem-separation IPC boundary by preventing raw, unexpected exception strings from being surfaced to callers, reducing the risk of leaking sensitive internal details (e.g., paths/implementation info) when separation fails.
Changes:
- Sanitize the generic exception path in
_stem_separation_worker()to emit a fixed, user-safe error message instead ofstr(error). - Update analysis-engine tests to assert the new sanitized message behavior for unexpected exceptions.
- Record the vulnerability/learning/prevention note in
.jules/sentinel.md.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| services/analysis-engine/src/bandscope_analysis/api.py | Replaces generic-exception IPC payload with a predefined safe message for unexpected failures. |
| services/analysis-engine/tests/test_api.py | Adjusts expectations to verify the sanitized message is returned for generic exceptions. |
| .jules/sentinel.md | Documents the information-leak scenario and the prevention approach for future reference. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH .jules/sentinel.md:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.jules/sentinel.md, services/analysis-engine/src/bandscope_analysis/api.py, services/analysis-engine/tests/test_api.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
30067c89d8ae514cd21ce04bc2f1170725bca475 - Workflow run: 28510661705
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file (2 files)"]
S1 --> I1["repository behavior"]
I1 --> R1["Review risk: Changed file (2 files)"]
R1 --> V1["required checks"]
Evidence --> S2["Test: test_api.py"]
S2 --> I2["regression suite"]
I2 --> R2["Review risk: Test: test_api.py"]
R2 --> V2["targeted test run"]
Contributor
OpenCode Review Overview
Pull request overviewOpenCode cannot approve yet because required coverage evidence did not pass. Review outcome1. HIGH .github/workflows/opencode-review.yml:1 - Coverage evidence did not prove required test/docstring evidence
Coverage evidenceCoverage Evidence
Python project dependencies (services/analysis-engine)
Python coverage with missing-line report (services/analysis-engine)
Python docstring coverage
JavaScript/TypeScript dependencies (npm ci)
Repository docstring coverage
JavaScript/TypeScript test coverage |
seonghobae
dismissed
github-actions[bot]’s stale review
Dismissed as a process-only OpenCode model-pool exhaustion review after all required checks passed and the only review thread was resolved. The user explicitly instructed that the review process is not a blocker.
Collaborator
Author
|
Current status after follow-up: all checks pass, the only review thread is resolved, and the process-only OpenCode model-pool change request was dismissed with rationale. Merge is still blocked by the repository ruleset requiring approval from someone other than the last pusher; even |
Acknowledged. The required code changes are complete and all checks have passed. I understand the remaining blocker is an external repository rule requiring human approval. No further action is required on my part. |
Collaborator
Author
Collaborator
Author
해당 PR이 다른 집중적인 PR(#497, #411)로 대체되었다는 내용을 확인했습니다. 안내해주셔서 감사합니다. |
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode cannot approve yet because required coverage evidence did not pass.
Review outcome
1. HIGH .github/workflows/opencode-review.yml:1 - Coverage evidence did not prove required test/docstring evidence
-
Problem: The required coverage-evidence job result was
failure, so OpenCode cannot establish approval sufficiency for this head. -
Root cause: Automated approval is only valid when the same-head coverage-evidence job proves supported repository test suites passed and configured docstring gates passed or were advisory, or reports not applicable because no supported source files or package manifests exist. Missing, failed, skipped, unavailable, or unsupported-tooling test evidence is a blocker.
-
Fix: Install or configure the repository test/docstring evidence tooling when source files or package manifests exist, rerun the current-head coverage-evidence job, and approve only after it reports
successwith required evidence or explicit no-source not-applicable evidence. -
Regression test: Keep the approval branch checking
needs.coverage-evidence.result == successbefore posting APPROVE, and publish REQUEST_CHANGES when coverage-evidence blocker states such as cancelled, skipped, failed, unsupported-tooling, or below-100 evidence are present. -
Result: REQUEST_CHANGES
-
Reason: coverage-evidence result was
failure, so required test/docstring evidence was not proven for current head4339a6de906b7684a1e2e5d377809ba9eb9299e4. -
Head SHA:
4339a6de906b7684a1e2e5d377809ba9eb9299e4 -
Workflow run: 28570511636
-
Workflow attempt: 1
Coverage evidence
Coverage Evidence
- Head SHA:
4339a6de906b7684a1e2e5d377809ba9eb9299e4 - Required test evidence: supported repository test suites must pass.
- Required docstring evidence: repository-owned docstring gates must pass when configured; otherwise docstring coverage is advisory.
Python project dependencies (services/analysis-engine)
Using CPython 3.12.3 interpreter at: /usr/bin/python3.12
Creating virtual environment at: services/analysis-engine/.venv
Resolved 49 packages in 0.70ms
Building bandscope-analysis @ file:///home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine
Downloading numpy (15.8MiB)
Downloading scikit-learn (8.5MiB)
Downloading scipy (33.6MiB)
Downloading ruff (10.7MiB)
Downloading soundfile (1.3MiB)
Downloading yt-dlp (3.0MiB)
Downloading mypy (13.0MiB)
Downloading numba (3.6MiB)
Downloading pygments (1.2MiB)
Downloading llvmlite (53.7MiB)
Downloaded soundfile
Downloaded pygments
Built bandscope-analysis @ file:///home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine
Downloaded numba
Downloaded ruff
Downloaded scikit-learn
Downloaded yt-dlp
Downloaded numpy
Downloaded llvmlite
Downloaded scipy
Downloaded mypy
Prepared 44 packages in 2.13s
Installed 44 packages in 84ms
+ audioread==3.1.0
+ bandit==1.9.4
+ bandscope-analysis==0.1.0 (from file:///home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine)
+ certifi==2026.2.25
+ cffi==2.0.0
+ charset-normalizer==3.4.6
+ coverage==7.13.4
+ decorator==5.2.1
+ idna==3.18
+ iniconfig==2.3.0
+ joblib==1.5.3
+ lazy-loader==0.5
+ librosa==0.11.0
+ librt==0.8.1
+ llvmlite==0.45.1
+ markdown-it-py==4.0.0
+ mdurl==0.1.2
+ msgpack==1.2.1
+ mypy==1.19.1
+ mypy-extensions==1.1.0
+ numba==0.62.1
+ numpy==2.3.5
+ packaging==26.0
+ pathspec==1.0.4
+ platformdirs==4.9.4
+ pluggy==1.6.0
+ pooch==1.9.0
+ pycparser==3.0
+ pygments==2.20.0
+ pytest==9.0.3
+ pytest-cov==7.0.0
+ pyyaml==6.0.3
+ requests==2.33.0
+ rich==15.0.0
+ ruff==0.15.5
+ scikit-learn==1.8.0
+ scipy==1.17.1
+ soundfile==0.13.1
+ soxr==1.0.0
+ stevedore==5.7.0
+ threadpoolctl==3.6.0
+ typing-extensions==4.15.0
+ urllib3==2.7.0
+ yt-dlp==2026.6.9
- Result: PASS
Python coverage with missing-line report (services/analysis-engine)
============================= test session starts ==============================
platform linux -- Python 3.12.3, pytest-9.0.3, pluggy-1.6.0
rootdir: /home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine
configfile: pyproject.toml
plugins: cov-7.0.0
collected 441 items
tests/test_activity.py ........ [ 1%]
tests/test_anchors.py .... [ 2%]
tests/test_api.py ......................... [ 8%]
tests/test_chord_recognizer.py .................... [ 12%]
tests/test_chords.py ......................... [ 18%]
tests/test_cli.py ................. [ 22%]
tests/test_health.py . [ 22%]
tests/test_pipeline_integration.py ......... [ 24%]
tests/test_pitch_tracker.py ............... [ 28%]
tests/test_priority.py ....... [ 29%]
tests/test_ranges.py ................... [ 34%]
tests/test_release_asset_selection.py ........ [ 35%]
tests/test_release_metadata.py ....... [ 37%]
tests/test_release_packaging.py ......... [ 39%]
tests/test_roles.py ....... [ 41%]
tests/test_roles_ml.py ... [ 41%]
tests/test_sections.py ... [ 42%]
tests/test_sections_utils.py .... [ 43%]
tests/test_segmenter.py ..................... [ 48%]
tests/test_separation.py ................................. [ 55%]
tests/test_supply_chain_policy.py ...................................... [ 64%]
........................................................................ [ 80%]
..................................................... [ 92%]
tests/test_temporal.py ......... [ 94%]
tests/test_transcription.py ... [ 95%]
tests/test_tuning.py ..... [ 96%]
tests/test_youtube.py ................ [100%]
=============================== warnings summary ===============================
tests/test_pipeline_integration.py::test_pipeline_without_detected_sections_falls_back
tests/test_roles.py::test_role_extractor_falls_back_when_activity_detection_fails
/home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine/.venv/lib/python3.12/site-packages/librosa/core/pitch.py:103: UserWarning: Trying to estimate tuning from empty frequency set.
return pitch_tuning(
tests/test_roles.py::test_role_extractor_falls_back_when_activity_detection_fails
/home/runner/work/bandscope/bandscope/pr-head/services/analysis-engine/.venv/lib/python3.12/site-packages/librosa/core/spectrum.py:266: UserWarning: n_fft=2048 is too large for input signal of length=100
warnings.warn(
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
================== 441 passed, 3 warnings in 97.23s (0:01:37) ==================
Name Stmts Miss Cover Missing
------------------------------------------------------------------------------------
src/bandscope_analysis/__init__.py 3 0 100%
src/bandscope_analysis/api.py 571 0 100%
src/bandscope_analysis/chords/__init__.py 5 0 100%
src/bandscope_analysis/chords/analyzer.py 116 0 100%
src/bandscope_analysis/chords/capo.py 10 0 100%
src/bandscope_analysis/chords/chord_recognizer.py 192 0 100%
src/bandscope_analysis/chords/model.py 15 0 100%
src/bandscope_analysis/cli.py 68 0 100%
src/bandscope_analysis/health.py 7 0 100%
src/bandscope_analysis/ranges/__init__.py 4 0 100%
src/bandscope_analysis/ranges/analyzer.py 77 0 100%
src/bandscope_analysis/ranges/model.py 19 0 100%
src/bandscope_analysis/ranges/pitch_tracker.py 54 0 100%
src/bandscope_analysis/roles/__init__.py 4 0 100%
src/bandscope_analysis/roles/activity.py 59 0 100%
src/bandscope_analysis/roles/extractor.py 118 0 100%
src/bandscope_analysis/roles/model.py 58 0 100%
src/bandscope_analysis/roles/priority.py 13 0 100%
src/bandscope_analysis/roles/tuning.py 11 0 100%
src/bandscope_analysis/sections/__init__.py 6 0 100%
src/bandscope_analysis/sections/anchors.py 5 0 100%
src/bandscope_analysis/sections/extractor.py 38 0 100%
src/bandscope_analysis/sections/model.py 35 0 100%
src/bandscope_analysis/sections/segmenter.py 140 0 100%
src/bandscope_analysis/sections/utils.py 8 0 100%
src/bandscope_analysis/separation/__init__.py 4 0 100%
src/bandscope_analysis/separation/audio_separator.py 145 0 100%
src/bandscope_analysis/separation/model.py 31 0 100%
src/bandscope_analysis/separation/separator.py 34 0 100%
src/bandscope_analysis/temporal/__init__.py 3 0 100%
src/bandscope_analysis/temporal/analyzer.py 49 0 100%
src/bandscope_analysis/temporal/model.py 9 0 100%
src/bandscope_analysis/transcription/__init__.py 2 0 100%
src/bandscope_analysis/transcription/api.py 11 0 100%
src/bandscope_analysis/youtube.py 81 0 100%
------------------------------------------------------------------------------------
TOTAL 2005 0 100%
- Result: PASS
Python docstring coverage
- Result: DEFERRED
- Reason: package.json defines check:python-docstrings; repository-owned docstring coverage runs after package dependency setup.
JavaScript/TypeScript dependencies (npm ci)
added 272 packages, and audited 275 packages in 8s
71 packages are looking for funding
run `npm fund` for details
found 0 vulnerabilities
- Result: PASS
Repository docstring coverage
> [email protected] check:python-docstrings
> sh -c 'cd services/analysis-engine && uv run ruff check src tests ../../scripts --select D100,D101,D102,D103,D104,D105,D106,D107'
All checks passed!
- Result: PASS
JavaScript/TypeScript test coverage
> [email protected] test
> npm run test --workspaces --if-present && sh -c 'cd services/analysis-engine && uv run pytest tests --cov=src/bandscope_analysis --cov-report=term-missing --cov-fail-under=100' --coverage
> @bandscope/[email protected] test
> node -e "require('node:fs').mkdirSync('coverage/.tmp', { recursive: true })" && vitest run --coverage
�[1m�[30m�[46m RUN �[49m�[39m�[22m �[36mv4.1.9 �[39m�[90m/home/runner/work/bandscope/bandscope/pr-head/apps/desktop�[39m
�[2mCoverage enabled with �[22m�[33mv8�[39m
�[32m✓�[39m src/lib/export.test.ts �[2m(�[22m�[2m16 tests�[22m�[2m)�[22m�[32m 16�[2mms�[22m�[39m
�[32m✓�[39m src/lib/analysis.test.ts �[2m(�[22m�[2m14 tests�[22m�[2m)�[22m�[32m 26�[2mms�[22m�[39m
�[32m✓�[39m src/features/workspace/Workspace.test.tsx �[2m(�[22m�[2m11 tests�[22m�[2m)�[22m�[33m 1810�[2mms�[22m�[39m
�[33m�[2m✓�[22m�[39m enables bass transcription from selected role metadata rather than role id text �[33m 449�[2mms�[22m�[39m
�[32m✓�[39m src/components/ui/ui-primitives.test.tsx �[2m(�[22m�[2m7 tests�[22m�[2m)�[22m�[32m 183�[2mms�[22m�[39m
�[32m✓�[39m src/i18n/index.test.ts �[2m(�[22m�[2m9 tests�[22m�[2m)�[22m�[32m 8�[2mms�[22m�[39m
�[90mstderr�[2m | src/App.test.tsx�[2m > �[22m�[2mApp�[2m > �[22m�[2mapplies pushed analysis status updates over the IPC event bridge
�[22m�[39mAn update to App inside a test was not wrapped in act(...).
When testing, code that causes React state updates should be wrapped into act(...):
act(() => {
/* fire events that update state */
});
/* assert on the output */
This ensures that you're testing the behavior the user would see in the browser. Learn more at https://react.dev/link/wrap-tests-with-act
## Changed-File Evidence Map
```mermaid
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file (26 files)"]
S1 --> I1["repository behavior"]
I1 --> R1["Review risk: Changed file (26 files)"]
R1 --> V1["required checks"]
Evidence --> S2["Workflow (14 files)"]
S2 --> I2["GitHub Actions review job"]
I2 --> R2["Review risk: Workflow (14 files)"]
R2 --> V2["actionlint plus required checks"]
Evidence --> S3["Docs (5 files)"]
S3 --> I3["operator or user guidance"]
I3 --> R3["Review risk: Docs (5 files)"]
R3 --> V3["docs review"]
Evidence --> S4["CI script (10 files)"]
S4 --> I4["review and security gate shell path"]
I4 --> R4["Review risk: CI script (10 files)"]
R4 --> V4["bash -n plus Strix self-test"]
Evidence --> S5["Test (7 files)"]
S5 --> I5["regression suite"]
I5 --> R5["Review risk: Test (7 files)"]
R5 --> V5["targeted test run"]
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.
🚨 Severity: CRITICAL/HIGH
💡 Vulnerability: The Python analysis engine was passing raw
Exceptionobjects (converted to strings) into user-facing IPC payloads when stem separation failed.🎯 Impact: Exposing raw exceptions can leak sensitive internal details, such as absolute file paths, memory addresses, or underlying system architecture, violating the Desktop App Security Policy for Python boundaries.
🔧 Fix: Caught generic exceptions and returned a sanitized, predefined error string ("An internal error occurred during stem separation.") rather than exposing
str(error)directly.✅ Verification: Ran
pytestinternally withinservices/analysis-engine/and executednpm run checkover the entire repository to guarantee safe execution. All tests pass successfully and verify the static error message generation.PR created automatically by Jules for task 8632839196680902626 started by @seonghobae