Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

axiom-shipping

skill · charleswiltgen/axiomMIT licenceAudited 31 Oct 2026 · source 363465e88c85

★ 1,242pushed today
✓SAFEGrade B · 89/100 · 31 Oct 2026 · 363465e
1,242repo stars · whole charleswiltgen/axiom

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 363465e88c85 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “axiom-shipping (charleswiltgen/axiom)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/charleswiltgen/axiom-shipping

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low3 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS4
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (4)

LOWPrompt injectionprompt.transfer_instruction · skills/app-store-submission.md:252
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
// POST to Apple's revoke endpoint with the user's token
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
INFOPrompt injectionprompt.authority_framing · skills/app-store-ref.md:395
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| Calendars (full access) | `NSCalendarsFullAccessUsageDescription` |
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.authority_framing · skills/app-store-ref.md:396
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| Reminders (full access) | `NSRemindersFullAccessUsageDescription` |
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.credential_read · skills/app-clips-ref.md:79
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| Keychain (access group) | App Clip ↔ app keychain sharing, iOS 15.4+ |
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 363465e88c85 · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishercharleswiltgen GitHub userOwner of the repository this skill is read from
  • Source foldercharleswiltgen/axiom/axiom-codex/skills/axiom-shippingThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict363465e88c85A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy…

---
name: axiom-shipping
description: Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy manifests, age ratings, export compliance.
license: MIT
---

# Shipping & App Store

**You MUST use this skill when preparing to submit ANY app, handling App Store rejections, or working on release workflow.**

**Bundled tools on Claude Code:** if `command -v <tool>` finds nothing (hooks off or `--bare`), use `<plugin-root>/tools/<tool>` in place of the bare name; `<plugin-root>` is two levels above this skill's `Base directory for this skill:` path.

<!-- AXIOM_AUDITOR_INLINE_BEGIN — rewritten for Codex by scripts/build-codex.ts; do not hand-edit -->
> **Auditors are skills here.** Where this router says "Launch `some-auditor` agent", invoke the
> matching Codex skill instead — same procedure, no Claude Code agent required.
>
> Available: `axiom-audit-iap`, `axiom-scan-security-privacy`.
>
> The ones that shell out — builds, tests, simulators, crash symbolication — need shell access to run.
<!-- AXIOM_AUDITOR_INLINE_END -->

## When to Use

Use this skill when you encounter:
- Preparing an app for App Store submission
- App Store rejection (any guideline)
- Metadata requirements (screenshots, descriptions, keywords)
- Privacy manifest and nutrition label questions
- Age rating and content classification
- Export compliance and encryption declarations
- EU DSA trader status
- Account deletion or Sign in with Apple requirements
- Build upload and processing issues
- App Review appeals
- WWDC25/WWDC26 App Store Connect changes
- First-time submission workflow

## Quick Reference

| Symptom / Task | Reference |
|----------------|-----------|
| How do I submit my app? | See `skills/app-store-submission.md` |
| Pre-flight checklist | See `skills/app-store-submission.md` |
| First-time submission | See `skills/app-store-submission.md` |
| Encryption compliance | See `skills/app-store-submission.md` |
| Accessibility Nutrition Labels | See `skills/app-store-submission.md` |
| Metadata field requirements | See `skills/app-store-ref.md` |
| Product Page Header, Asset Library, search visuals `OS27` | See `skills/app-store-ref.md` (Part 11) |
| Retention Messaging (subscription cancellation flow) `OS27` | See `skills/app-store-ref.md` (Part 11) |
| Group / volume subscription selling (ABM, ASM, volume pricing) `OS27` | See `skills/app-store-ref.md` (Part 11) |
| Guideline number lookup | See `skills/app-store-ref.md` |
| Privacy manifest schema | See `skills/app-store-ref.md` |
| Age rating tiers | See `skills/app-store-ref.md` |
| EU DSA compliance | See `skills/app-store-ref.md` |
| WWDC25/WWDC26 ASC changes | See `skills/app-store-ref.md` |
| App was rejected | See `skills/app-store-diag.md` |
| Guideline 2.1/4.2/4.3 rejection | See `skills/app-store-diag.md` |
| Writing an appeal | See `skills/app-store-diag.md` |
| Repeated rejections | See `skills/app-store-diag.md` |
| App Review Guidelines reference | See `skills/app-review-guidelines.md` |
| Expert review checklist | See `skills/expert-review-checklist.md` |
| Crash data in App Store Connect | See `skills/app-store-connect-ref.md` |
| TestFlight crash reports | See `skills/app-store-connect-ref.md` |
| ASC metrics dashboards | See `skills/app-store-connect-ref.md` |
| Beta tester crash report, local Organizer crash corpus (.xccrashpoint) | See `skills/testflight-triage.md` |
| Production corpus triage (Sentry, ASC — multiple grouped issues) | See `skills/production-triage.md` + `triage-analyzer` agent or `axiom-analyze-triage` |
| Crash log symbolication (.ips / MetricKit / .crash) | See axiom-tools (skills/xcsym-ref.md) or `axiom-analyze-crash`; `skills/testflight-triage.md` for the full TF workflow |
| Automate App Store Connect | See `skills/asc-mcp.md` |
| Submit build programmatically | See `skills/asc-mcp.md` |
| Manage TestFlight via MCP | See `skills/asc-mcp.md` |
| ITMS signing error on upload | See axiom-security (skills/code-signing-diag.md) |
| Certificate/profile mismatch | See axiom-security (skills/code-signing-diag.md) |
| Code signing setup | See axiom-security (skills/code-signing.md) |
| App Clips (size tiers, invocation, AASA, launch experience) | See `skills/app-clips.md` |
| App Clip entitlements / size / data-sharing reference | See `skills/app-clips-ref.md` |
| Apple Pay / Wallet / Tap to Pay payments | See `axiom-payments` suite |
| Shipping update with Claude model-ID change (4.6 → 4.7, etc.) | See **`claude-api`** skill (external) + this skill for submission |
| Switching cloud AI provider in-app (OpenAI → Claude, etc.) | See **`claude-api`** skill (external) + this skill for submission |

## Routing Logic

### 1. Pre-Submission Preparation → **app-store-submission**

**Triggers**:
- "How do I submit my app?"
- "What do I need before submitting?"
- Preparing for first submission
- Pre-flight checklist needed
- Screenshot requirements
- Metadata completeness check
- Encryption compliance questions
- Accessibility Nutrition Labels
- Privacy manifest requirements for submission

**Why app-store-submission**: Discipline skill with 8 anti-patterns, decision trees, and pressure scenarios. Prevents the mistakes that cause 90% of rejections.

**Reference**: `skills/app-store-submission.md`

---

### 2. Metadata, Guidelines, and API Reference → **app-store-ref**

**Triggers**:
- "What fields are required in App Store Connect?"
- "What's the max length for app description?"
- Specific guideline number lookup
- Privacy manifest schema details
- Age rating tiers and questionnaire
- IAP submission metadata
- EU DSA compliance details
- Build upload methods
- WWDC25 and WWDC26 changes to App Store Connect

**Why app-store-ref**: 11-part reference covering every metadata field, guideline, and compliance requirement with exact specifications.

**Reference**: `skills/app-store-ref.md`

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 363465e

Download folder ↗
claude mcp add --transport stdio --scope user asc-mcp -- ~/.mint/bin/asc-mcp

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 363465e88c85 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 363465e88c85

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/charleswiltgen/axiom-shipping/badge.svg)](https://modelsatlas.com/skills/charleswiltgen/axiom-shipping/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/charleswiltgen/axiom-shipping/badge.svg)](https://modelsatlas.com/skills/charleswiltgen/axiom-shipping/)

Questions about axiom-shipping

What does the axiom-shipping skill do?
Battle-tested Claude Code skills for modern xOS (iOS, iPadOS, watchOS, tvOS) development
Is axiom-shipping safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can axiom-shipping access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does axiom-shipping work with?
Its documentation mentions claude-code, codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (363465e88c85), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.