qwen-image-pro

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These URLs belong to a small third‑party service that offers a remote installer (curl | sh from cli.inference.sh) and downloadable binaries from dist.inference.sh — a pattern that can distribute malware if the provider or update channel is compromised, although included checksum verification and consistent subdomains reduce but do not eliminate the risk.

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

• Third-party content exposure detected (high risk: 0.70). The skill accepts arbitrary external image URIs via the "reference_images" input (see the "Image Editing (Style Transfer)" example and the Input Options table), so it can fetch untrusted public images from third-party URLs which the model will read/interpret and which can materially influence generation behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The Quick Start instructs users to run "curl -fsSL https://cli.inference.sh | sh" which fetches and executes remote code from https://cli.inference.sh (and pulls binaries from dist.inference.sh) as a required install step for running the skill, so this external URL can execute remote code at runtime.