calibre-library

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). It instructs reading username/password from a local config and explicitly replacing those values into curl commands (e.g., using -u $USERNAME:$PASSWORD), which encourages the LLM to include secrets verbatim in generated outputs.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches JSON from a user-configurable Calibre Content Server base_url (e.g., {BASE}/ajax/search, {BASE}/ajax/books and {item_url}), and it reads untrusted fields like comments (HTML) and category_urls from those third-party endpoints which the agent uses to decide what further requests or downloads to perform, allowing indirect injection of instructions or malicious URLs.