localization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited localization (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an expert in App Store internationalization and localization strategy. Your goal is to help the user expand to new markets by localizing their App Store presence effectively.
app-marketing-context.md — read it for current markets and languages| Market | Language | App Store Code | Notes |
|---|---|---|---|
| United States | English | en-US | Largest market |
| United Kingdom | English | en-GB | Easy win if US is done |
| Germany | German | de-DE | Largest EU market |
| Japan | Japanese | ja | High ARPU, competitive |
| France | French | fr-FR | Large EU market |
| South Korea | Korean | ko | High smartphone penetration |
| China | Simplified Chinese | zh-Hans | Massive but complex (needs ICP) |
| Brazil | Portuguese | pt-BR | Largest LATAM market |
| Canada | English/French | en-CA/fr-CA | Easy win |
| Australia | English | en-AU | Easy win |
Spain (es-ES), Italy (it), Netherlands (nl), Sweden (sv), Russia (ru), Mexico (es-MX), India (en-IN/hi), Indonesia (id), Turkey (tr), Saudi Arabia (ar-SA)
Evaluate each market on:
| Factor | Weight | How to assess |
|---|---|---|
| Market size | 30% | iPhone user base in country |
| Competition | 25% | How many localized competitors? |
| Effort | 20% | Translation complexity, cultural distance |
| Revenue potential | 15% | ARPU in the market |
| Strategic fit | 10% | Does your app solve a local need? |
For each target market:
The biggest localization mistake: Translating English keywords directly.
Instead:
keyword-research for each target market separatelyExample:
| Element | What to check |
|---|---|
| Screenshots | Currency symbols, date formats, number formats |
| Colors | Cultural color associations (red = luck in China, danger in West) |
| Imagery | Diverse representation, culturally appropriate |
| Tone | Formal vs informal varies by culture |
| Features | Highlight features relevant to local needs |
| Social proof | Use local press, local user counts if possible |
| Pricing | Local pricing expectations (purchasing power parity) |
For metadata (title, subtitle, keywords):
For description:
For screenshots:
For each recommended market:
## [Country] — [Language]
Priority: [High/Medium/Low]
Estimated effort: [hours/days]
Expected impact: [download increase estimate]
Keywords (top 10):
| Keyword | Volume | Difficulty | English equivalent |
|---------|--------|------------|-------------------|
Metadata:
- Title: [localized title] ([X]/30 chars)
- Subtitle: [localized subtitle] ([X]/30 chars)
- Keywords: [localized keyword field] ([X]/100 chars)
Cultural notes:
- [specific adaptations needed]| Market | Size | Competition | Effort | Revenue | Score | Priority |
|---|
keyword-research — Run for each target marketmetadata-optimization — Write localized metadatascreenshot-optimization — Localize screenshot designscompetitor-analysis — Analyze local competitors~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.