home-assistant-integration

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

• Third-party content exposure detected (high risk: 0.85). At runtime the required workflow instructs fetching markdown from https://raw.githubusercontent.com/home-assistant/developers.home-assistant/... (public web content) and using that fetched prose as input context, which is an outsider-authored source.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch and use remote markdown from https://raw.githubusercontent.com/home-assistant/developers.home-assistant/master/docs/ (and specific raw doc files) to guide coding decisions, so remote content directly controls the agent's prompts and behavior.