Leaderboard github.com
Alisa0808/vox-director
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
unreviewed-ai-risk
AI provenance
94%
explicit
- Confidence
- 77%
- Coverage
- 100%
Estimated share of AI-generated code. Explicit attribution is a lower bound.
Code quality
34/100
poor
- Confidence
- 90%
- Coverage
- 100%
Complexity, duplication, lint density, tests, CI, docs and review process.
Security
77/100
adequate
- Confidence
- 85%
- Coverage
- 100%
Secrets, static analysis, vulnerable dependencies, CI and supply-chain posture.
- Repository: https://github.com/Alisa0808/vox-director
- Commit:
6a85a7c341610442a6a5b1885e6e0217ab82a11f - Generated: 2026-11-14T00:00:37+00:00
- Scorer 0.1.0, scoring prov-4+qual-2+sec-2, report schema v2
Scores
Unreviewed AI code risk: a large share of this code is explicitly AI-attributed, and its tests or review process are weak while quality or security scores are low.
| Pillar | Score | Signal | Confidence | Coverage |
|---|---|---|---|---|
| AI provenance (estimated AI-generated share) | 94 | explicit | 77% | 100% |
| Code quality | 34 | poor | 90% | 100% |
| Security | 77 | adequate | 85% | 100% |
AI provenance
Explicit AI attribution on 94% of first-party code added; an estimated 94% including velocity signals.
- Explicitly attributed share (lower bound): 93.5%
- Unattributed share in AI-consistent velocity bursts: 0.0%
- Estimated AI-generated share: 93.5%
| AI tool | Attributed commits | Lines added |
|---|---|---|
| Claude Code | 29 | 3,300 |
- AI tooling configured in repo: generic-agent
Current source lines last changed by AI-attributed commits: 3,093 of 3,309.
Too few lines in one group to compare finding densities.
| Month | Lines added | Attributed to AI |
|---|---|---|
| 2026-07 | 2,809 | 92% |
| 2026-10 | 720 | 100% |
Evidence
- Claude Code: trailer 'Co-Authored-By: Claude' (6a85a7c34161)
- Claude Code: trailer 'Co-authored-by: Claude' (668ec3946fe0)
- Claude Code: trailer 'Co-authored-by: Claude' (8b034354dc44)
- Claude Code: trailer 'Co-Authored-By: Claude' (a75167b0ef15)
- Claude Code: trailer 'Co-Authored-By: Claude' (922b87f2ad16)
- Claude Code: trailer 'Co-Authored-By: Claude' (27822c6ef959)
- Claude Code: trailer 'Co-Authored-By: Claude' (3ec747936eb7)
- Claude Code: trailer 'Co-Authored-By: Claude' (77bc68ff6840)
- Claude Code: PR description attribution (0f66dc444fc1)
- Claude Code: trailer 'Co-Authored-By: Claude' (c22681a6d101)
- Claude Code: trailer 'Co-authored-by: Claude' (186587cb0291)
- Claude Code: trailer 'Co-Authored-By: Claude' (f4314a464ecf)
- Claude Code: trailer 'Co-Authored-By: Claude' (4ec7dac870d3)
- Claude Code: trailer 'Co-Authored-By: Claude' (ad97ffdd38e5)
- Claude Code: trailer 'Co-Authored-By: Claude' (1f42111e3765)
AI provenance describes how code was produced; it is not a quality judgment. Unless attribution is explicit, these are signals consistent with AI generation, not proof. Squash/rebase workflows, imported code, and rewritten history reduce accuracy.
Code quality
Code quality is poor: test-to-source ratio 0.00, no CI test run detected; 25% of function code in complex or long functions; 4% duplicated lines. Weakest area: testing.
| Area | Score |
|---|---|
| Complexity (lizard) | 48 |
| Duplication | 80 |
| Code smells (Opengrep) | 7 |
| Tests and CI | 0 |
| Documentation | 65 |
| Type safety | 40 |
| Process (Scorecard review/maintenance) | n/a |
- Functions: 119; mean complexity 4.5, 90th percentile 10; 6 complex and 0 long functions
- Duplicated lines: 3.7% of 2,630 compared
- Tests: 0 test lines for 3,309 source lines (ratio 0.00); CI test commands: none detected; 0% of recent source commits also change tests
- Docs missing or thin: contributing, changelog
Most complex functions:
- run in scripts/host_clips.py: complexity 32, 95 lines
- run in scripts/assemble.py: complexity 23, 96 lines
- run in scripts/clips.py: complexity 22, 77 lines
- run in scripts/host_plates.py: complexity 21, 65 lines
- validate in scripts/host.py: complexity 20, 36 lines
Security
Security posture is adequate: 1 high-severity SAST findings. Weakest area: posture.
| Area | Score |
|---|---|
| Secrets (gitleaks, tree + history) | 100 |
| Static analysis (Opengrep) | 88 |
| Vulnerable dependencies (OSV) | n/a |
| CI workflows (zizmor) | n/a |
| Posture (policy, updates, signing, lockfiles) | 0 |
| OpenSSF Scorecard | n/a |
- Posture checks passed: none; missing: security policy, dependency updates, signed commits, lockfiles
Top findings
| Severity | Finding | Location |
|---|---|---|
| high | opengrep/python.lang.security.audit.dangerous-subprocess-use-audit: Detected subprocess function 'run' without a static string. If this data can be controlled by a malicious actor, it may be an instance of command injection. Audit the use of this call to ensure it is not controllable by an external resource. You may consider using 'shlex.escape()'. [confidence low] |
scripts/host_clips.py:37 |
| medium | opengrep/python.lang.security.audit.dynamic-urllib-use-detected: Detected a dynamic value being used with urllib. urllib supports 'file://' schemes, so a dynamic value controlled by a malicious actor may allow them to read arbitrary files. Audit uses of urllib calls to ensure user data cannot control the URLs, or consider using the 'requests' library instead. [confidence low] |
scripts/atlas_cloud.py:53 |
| medium | opengrep/python.lang.security.audit.dynamic-urllib-use-detected: Detected a dynamic value being used with urllib. urllib supports 'file://' schemes, so a dynamic value controlled by a malicious actor may allow them to read arbitrary files. Audit uses of urllib calls to ensure user data cannot control the URLs, or consider using the 'requests' library instead. [confidence low] |
scripts/atlas_cloud.py:64 |
Static signals only: the scorer never runs the project's code. Secret findings are pattern matches that were not verified, and secret values are never stored.
Repository profile
- Source lines: 3,309; test lines: 0
| Language | Lines |
|---|---|
| Python | 3,309 |