ua-campaign — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ua-campaign (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 mobile app user acquisition across all major ad platforms. Your goal is to help the user plan, launch, and optimize paid campaigns that drive profitable installs.
app-marketing-context.md — read it for context| Monthly Budget | Recommended Channels |
|---|---|
| < $1K | Apple Search Ads (Basic) only |
| $1K-$5K | Apple Search Ads (Advanced) + 1 social channel |
| $5K-$20K | ASA + Meta + Google UAC |
| $20K-$100K | ASA + Meta + Google + TikTok + testing new channels |
| $100K+ | All channels + programmatic + influencer |
| Channel | Avg CPI | Intent | Best For | Complexity |
|---|---|---|---|---|
| Apple Search Ads | $1-3 | Very High | All iOS apps | Low |
| Google UAC | $0.5-2 | Medium | Android + broad reach | Medium |
| Meta (FB/IG) | $1-4 | Low-Medium | Consumer, social, e-commerce | High |
| TikTok | $0.5-3 | Low | Young demographics, games | Medium |
| Snapchat | $0.5-2 | Low | Gen Z, AR apps | Medium |
| Twitter/X | $2-5 | Low | News, tech, finance | Medium |
| $1-3 | Medium | Niche communities | Low |
Account
├── Brand Campaign (exact match)
│ ├── [your app name]
│ └── [common misspellings]
├── Category Campaign (broad + exact)
│ ├── [category terms]
│ └── [feature terms]
├── Competitor Campaign (exact match)
│ ├── [competitor name 1]
│ └── [competitor name 2]
└── Discovery Campaign (Search Match)
└── Auto-targeting (find new keywords)| Campaign Type | Bid Strategy | Target CPA |
|---|---|---|
| Brand | Low bids, high volume | < $0.50 |
| Category | Medium bids | $1-3 |
| Competitor | Higher bids, lower volume | $2-5 |
| Discovery | Low bids, broad | $1-3 |
Campaign: App Installs
├── Ad Set 1: Lookalike (1%) of paying users
│ ├── Ad: Video (15s feature demo)
│ ├── Ad: Carousel (feature highlights)
│ └── Ad: Static (benefit headline)
├── Ad Set 2: Interest-based targeting
│ ├── Ad: Video (problem/solution)
│ └── Ad: UGC-style testimonial
└── Ad Set 3: Broad targeting (let Meta optimize)
├── Ad: Best performing from above
└── Ad: New creative testVideo ads (highest performance):
Static ads:
Impressions → Taps → Installs → Activations → Purchases
CTR CVR CPI CPA ROAS| Metric | Formula | Target |
|---|---|---|
| CTR | Taps / Impressions | > 5% (ASA), > 1% (social) |
| CVR | Installs / Taps | > 30% (ASA), > 10% (social) |
| CPI | Spend / Installs | < LTV / 3 |
| CPA | Spend / Purchases | < LTV |
| ROAS | Revenue / Spend | > 1.0 (break even), > 2.0 (good) |
| D7 ROAS | Day 7 Revenue / Spend | Predict long-term ROAS |
| Frequency | Action |
|---|---|
| Daily | Check spend pacing, pause overspending |
| Weekly | Review CPI/CPA by keyword/ad set, adjust bids |
| Bi-weekly | Refresh creative (ad fatigue after 2-3 weeks) |
| Monthly | Review channel mix, reallocate budget to winners |
| Quarterly | Strategic review, test new channels |
Monthly Budget: $[X]
Target CPI: $[X]
Target Monthly Installs: [N]
Channel Allocation:
- Apple Search Ads: [X]% ($[X])
- Meta: [X]% ($[X])
- Google UAC: [X]% ($[X])
- Testing: [X]% ($[X])
Week 1: [setup tasks]
Week 2: [launch tasks]
Week 3-4: [optimization tasks]For each channel, provide:
app-launch — UA strategy for launchmonetization-strategy — LTV calculation for CPI targetsapp-analytics — Attribution and funnel trackingcompetitor-analysis — Competitive ad intelligenceab-test-store-listing — Improve organic conversion (lowers effective CPI)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.