comfy-tools-setup

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly installs code from a public GitHub URL (uv tool install git+https://github.com/quinteroac/comfy-agent-tools) and references switching to a comfy-model-downloader to fetch public model checkpoints, which means it fetches and executes untrusted, user-generated third‑party content that can change tool behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs a runtime install from a remote git URL (uv tool install git+https://github.com/quinteroac/comfy-agent-tools), which fetches and installs remote code that will be executed and is required for the skill to operate.