sprites-dev

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses the WebFetch tool to fetch public documentation pages (e.g., https://docs.sprites.dev/llms.txt / llms-full.txt) at runtime, so the LLM ingests outsider-authored free text from the public web.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching live documentation at runtime (e.g., https://docs.sprites.dev/llms.txt and https://docs.sprites.dev/llms-full.txt, plus pages such as https://docs.sprites.dev/index.md) via WebFetch and instructs using that fetched content to form responses, meaning external documents directly control agent prompts.