TestCAUTION
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
Overview
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
ece51da22674OBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: test
description: Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
disable-model-invocation: false
argument-hint: [unit|e2e|all|FilterName]
allowed-tools: Bash
---
# Test
Run unit and/or E2E tests.
- `unit` (default): Quick tests, no model downloads. CI-safe.
- `e2e`: Full pipeline tests with real models, via `scripts/test_e2e_isolated.sh`
— one process per E2E suite. Never use plain `swift test` for the full E2E
suite: models accumulate in a single xctest process and can exhaust system
memory (observed: machine reboot).
- `all`: Both unit and E2E (unit phase once, then isolated E2E suites).
- Any other argument: passed as `--filter` to swift test.
```bash
arg="${ARGUMENTS:-unit}"
case "$arg" in
unit) swift test --skip E2E 2>&1 | tail -20 ;;
e2e) swift build --build-tests --disable-sandbox && ./scripts/build_mlx_metallib.sh debug && E2E_SKIP_UNIT=1 scripts/test_e2e_isolated.sh 2>&1 | tail -40 ;;
all) swift build --build-tests --disable-sandbox && ./scripts/build_mlx_metallib.sh debug && scripts/test_e2e_isolated.sh 2>&1 | tail -40 ;;
*) swift test --filter "$arg" 2>&1 | tail -20 ;;
esac
```
E2E test classes MUST be prefixed with `E2E`. Unit test classes must NOT contain `E2E`.Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.codex/skills/speech-swift-benchmark
.codex/skills/speech-swift-build
.codex/skills/speech-swift-review-pr
.codex/skills/speech-swift-test
.github/copilot-instructions.md
Gates applied: no_behavioural_pass.
ece51da22674full audit observations/trust-audit/skill/soniqo__test.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | ece51da22674 | CAUTION | B | 89 | first audit |
Questions
What does the Test skill do?
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
Is Test safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Test access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (ece51da22674), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.