admin-devops

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's required workflows and scripts explicitly download and execute public third‑party content (e.g., curl | bash and GitHub/CDN URLs in references/ENHANCED_SETUP.md and BUNDLED_SCRIPTS.md, cloudflared/Cloudflare API calls, and cntb GitHub downloads in references/contabo.md), and the agent is expected to parse those external responses and run follow‑on provisioning/installation steps—so untrusted web content can materially change agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill contains explicit runtime commands that fetch and execute remote scripts (e.g., "curl -fsSL https://cdn.coollabs.io/coolify/install.sh | bash" and "curl -fsSL https://raw.githubusercontent.com/YOUR-ORG/vibeskills-demo/main/.claude/skills/admin-devops/scripts/coolify-enhanced-setup.sh | bash"), which clearly download external content that is executed during runtime and thus meet the criteria for a high-risk external dependency.