ai-social-media-content

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The URLs point to an unverified third‑party domain (inference.sh) and its cloud subdomain and the skill explicitly instructs piping a remote shell script into sh (curl | sh), a high‑risk pattern for delivering malware; the image/placeholder links don’t mitigate that risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts and processes arbitrary external media URLs (e.g., "image_url": "https://your-avatar.jpg" in the "Create AI avatar" workflow and "media_url": "" for tweets), so the agent will fetch and interpret untrusted third-party content.