engremran07/gsmvault/ads-compliance-scanning
Claude Code and agent skill by engremran07/gsmvault
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Ad content scanning: malvertising prevention. Use when: validating ad creatives, scanning for malicious scripts, blocking harmful ad content.
Install
npx vskill@latest install engremran07/gsmvault/ads-compliance-scanningSKILL.md
The same SKILL.md was published earlier as engremran07/gsmvault/ads-compliance-scanning.
Ad Content Scanning
When to Use
- Validating
AdCreativecontent before serving - Scanning
AdUnit.render_codefor malicious JavaScript - Blocking creatives that redirect or inject unwanted content
- Preventing supply-chain attacks via third-party ad code
Rules
- All
render_codeandAdCreativeHTML sanitized withsanitize_ad_code()fromapps.core.sanitizers - Block ad code containing:
document.write,eval(),window.location, crypto miners - Direct sale creatives (
network_type = "direct") MUST pass content scan - Auto-rejecting creatives with external scripts not on allow-list
- Log blocked creatives to
AdEvent(event_type="blocked")
Patterns
Creative Content Validation
Pre-Serve Scan in Rotation
Anti-Patterns
- Serving
render_codewithout sanitization — XSS vector - Allowing
document.writein ad scripts — breaks page rendering - No logging of blocked creatives — can't identify malvertising sources
- Trusting all network-provided ad code without scanning
Quality Gate
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.github/skills/ads-compliance-scanning/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/engremran07/gsmvault/ads-compliance-scanning)