media-processing

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs installing and using third-party packages and models from the open web (e.g., "npm install -g rmbg-cli" in SKILL.md and the rmbg docs that say "Models download automatically on first use" with a curl to unpkg in references/rmbg-background-removal.md and scripts that auto-install rmbg-cli), so it fetches and executes untrusted third-party content that can materially alter tool behavior at runtime.