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

Agent skill · Audited from source

release-review

skill · rshankras/claude-code-apple-skillsMIT licenceAudited 31 Oct 2026 · source 7fd70e317e5c

★ 843pushed 99 days ago
!CAUTIONGrade C · 79/100 · 3 findings · 7fd70e3
843repo stars · whole rshankras/claude-code-apple-skills

Is it safe? With care — CAUTION, grade C (79/100). We read this skill's source at commit 7fd70e317e5c and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 3 findings, 1 critical or high. What it does: Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an app for release, want a critical review, or before App…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “release-review (rshankras/claude-code-apple-skills)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/rshankras/release-review

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score79/100!CAUTION C
0 critical1 high0 medium0 low2 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade C is shared by 100 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 directivesFAIL3
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: instruction override, no behavioural pass.

Findings (3)

HIGHPrompt injectionprompt.override · security-checklist.md:175
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- [ ] Jailbreak detection considered (if needed)
Why
asks the agent to drop prior instructions or safety
Fix
remove the instruction
INFOPrompt injectionprompt.credential_read · privacy-checklist.md:163
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
// Users will see: "[App] wants to access [Item] in your keychain"
Why
asks the agent to read credentials
Fix
—
INFOPrompt injectionprompt.credential_read · privacy-checklist.md:165
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Text("On first launch, macOS will ask to access credentials from your Keychain. Click 'Always Allow' for permanent access.")
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 7fd70e317e5c · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherrshankras GitHub userOwner of the repository this skill is read from
  • Source folderrshankras/claude-code-apple-skills/skills/release-reviewThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict7fd70e317e5cA new audit runs when the source changes
  • Repository statusNot archivedLast push 99 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an app for release, want a critical review, or before App…

---
name: release-review
description: Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an app for release, want a critical review, or before App Store submission.
allowed-tools: [Read, Glob, Grep]
last_verified: 2026-07-16
review_by: 2027-06-22
os_version: iOS 27 / macOS 27
---

# Release Review for Apple Platforms

Performs a comprehensive pre-release audit of macOS and iOS applications from a senior developer's perspective. Identifies critical issues that could cause rejection, security vulnerabilities, privacy concerns, and UX problems—with actionable fixes.

## When This Skill Activates

Use this skill when the user:
- Says "review for release", "release review", or "pre-release audit"
- Asks for "senior developer review" or "critical review"
- Mentions preparing for "App Store", "TestFlight", or "notarization"
- Wants to know what "power users might complain about"
- Asks to "review before shipping" or "check before release"

## Review Process

### Phase 1: Project Discovery

First, understand the project:

```bash
# Find project type
Glob: **/*.xcodeproj or **/*.xcworkspace
Glob: **/Info.plist
Glob: **/project.pbxproj
```

Identify:
- Platform (macOS, iOS, or both)
- App type (standard app, menu bar app, widget, extension)
- Distribution method (App Store, direct download, TestFlight)

### Phase 2: Security Review

Load and apply: **security-checklist.md**

Key areas:
- Credential storage (Keychain patterns, no hardcoded secrets)
- Data transmission (HTTPS, certificate validation)
- Input validation (injection prevention)
- Entitlements audit
- Hardened runtime (macOS)

### Phase 3: Privacy Review

Load and apply: **privacy-checklist.md**

Key areas:
- Data collection transparency
- Privacy manifest (iOS 17+)
- User consent flows
- Third-party SDK disclosure
- GDPR compliance basics

### Phase 4: UX Polish Review

Load and apply: **ux-polish-checklist.md**

Key areas:
- First launch / onboarding
- Empty states and error handling
- Loading states
- Text truncation and accessibility
- Platform-specific UX patterns

### Phase 5: Distribution Review

Load and apply: **distribution-checklist.md**

Key areas:
- Bundle identifier format
- Code signing configuration
- Info.plist completeness
- App icons
- Platform-specific requirements (notarization, App Store)

### Phase 6: API Design Review

Load and apply: **api-design-checklist.md**

Key areas:
- User-Agent headers (honest identification)
- Error handling patterns
- Token expiration handling
- Rate limiting
- Offline handling

## Output Format

Present findings in this structure:

```markdown
# Release Review: [App Name]

**Platform**: macOS / iOS / Universal
**Distribution**: App Store / Direct Download / TestFlight
**Review Date**: [Date]

## Summary

| Priority | Count |
|----------|-------|
| Critical | X |
| High | X |
| Medium | X |
| Low | X |

---

## 🔴 Critical Issues (Must Fix)

Issues that will cause rejection, crashes, or security vulnerabilities.

### [Category]: [Issue Title]

**File**: `path/to/file.swift:123`
**Impact**: [Why this matters]

**Current Code**:
```swift
// problematic code
```

**Suggested Fix**:
```swift
// fixed code
```

---

## 🟠 High Priority (Should Fix)

Issues that significantly impact user experience or trust.

[Same format as above]

---

## 🟡 Medium Priority (Fix Soon)

Issues that should be addressed but won't block release.

[Same format as above]

---

## 🟢 Low Priority / Suggestions

Nice-to-have improvements and polish.

[Same format as above]

---

## ✅ Strengths

What the app does well:
- [Strength 1]
- [Strength 2]
- [Strength 3]

---

## Recommended Action Plan

1. **[Critical]** [First thing to fix]
2. **[Critical]** [Second thing to fix]
3. **[High]** [Third thing to fix]
...
```

## Priority Classification

### 🔴 Critical
- Security vulnerabilities (credential exposure, injection)
- Crashes or data loss scenarios
- App Store rejection causes
- Privacy violations
- Hardcoded secrets or spoofed identifiers

### 🟠 High
- Poor error handling (silent failures)
- Missing user consent or transparency
- Accessibility blockers
- Missing required Info.plist keys
- Broken functionality

### 🟡 Medium
- Incomplete onboarding
- Suboptimal UX patterns
- Missing empty states
- Performance concerns
- Minor accessibility issues

### 🟢 Low
- Code style improvements
- Additional features
- Polish and refinement
- Documentation improvements

## Platform-Specific Considerations

### macOS
- Menu bar app window activation (`NSApp.activate`)
- Sandbox exceptions justification
- Notarization requirements
- Hardened runtime
- Developer ID signing
- DMG/installer considerations

### iOS
- App Tracking Transparency
- Privacy nutrition labels
- Launch screen requirements
- Export compliance
- In-app purchase requirements
- TestFlight configuration

## References

- **security-checklist.md** - Detailed security review items
- **privacy-checklist.md** - Privacy and data handling
- **ux-polish-checklist.md** - User experience review
- **distribution-checklist.md** - Release and distribution
- **api-design-checklist.md** - Network and API patterns

Excerpt, first 5,231 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 7fd70e3

Download folder ↗
git clone https://github.com/rshankras/claude-code-apple-skills
git -C claude-code-apple-skills checkout 7fd70e317e5c

The author documents no install command, so this uses the repository directly. Our verdict covers commit 7fd70e317e5c 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
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION C 79 / 100

    first audit · source 7fd70e317e5c

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION CMODELSATLASCAUTION · C
[![ModelsAtlas: CAUTION C](https://modelsatlas.com/skills/rshankras/release-review/badge.svg)](https://modelsatlas.com/skills/rshankras/release-review/)

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

shared✓SAFE

rshankras/claude-code-apple-skills

Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.

★ 844Grade B
monetization✓SAFE

rshankras/claude-code-apple-skills

Monetization strategy for iOS/macOS apps. Covers readiness assessment, pricing model selection, tier structuring, free trial strategy, and implementation guidance. Use when deciding what to charge, how to price, or…

★ 843Grade B
security✓SAFE

rshankras/claude-code-apple-skills

Security category index for Apple platforms. Routes to the privacy-manifests skill. General secure-storage/biometrics/ATS guidance was retired in the 2026 blind-test audit — current models cover it natively.

★ 843Grade B
legal✓SAFE

rshankras/claude-code-apple-skills

Legal document generation and compliance guidance for indie Apple developers. Covers privacy policies, terms of service, EULAs, GDPR/CCPA/DPDP compliance, and Apple App Store legal requirements. Use when user needs…

★ 838Grade B
growth✓SAFE

rshankras/claude-code-apple-skills

Growth skills for indie Apple developers — user acquisition, analytics interpretation, press/media outreach, community building, and indie business operations. Also covers the stage-by-stage store-growth audit and the…

★ 837Grade B
design✓SAFE

rshankras/claude-code-apple-skills

Design skills for Apple platform UI — Liquid Glass, animations, game feel (haptics, sound, celebrations), UI prototyping, UX writing, SF Symbols, and typography. Use when implementing design language features, adding…

★ 836Grade B

Add this badge to your README

[![ModelsAtlas: CAUTION C](https://modelsatlas.com/skills/rshankras/release-review/badge.svg)](https://modelsatlas.com/skills/rshankras/release-review/)

Questions about release-review

What does the release-review skill do?
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation, App Store optimization, and more
Is release-review safe to install?
With care. The audit graded it C (79/100) and found 3 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can release-review access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does release-review work with?
Its documentation mentions claude-code. 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 (7fd70e317e5c), 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.