pp-goodreads

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to run the goodreads-pp-cli commands (via --agent), which fetches Goodreads pages/feeds at runtime and returns their contents as JSON results into the agent context; those page bodies are outsider-authored free text (Goodreads users/website content) and can include prompt-injection strings.