wordpress-publisher

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly asks the user for an application password and shows code that embeds the password directly in constructor/API calls and test requests, which requires the LLM to handle and potentially output the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and analyzes content from user-specified WordPress sites via the REST API (e.g., wp.get_categories_with_details(), wp.fetch_preview(), wp.verify_published_post in SKILL.md), and that untrusted, user-generated site content is parsed and used to suggest categories, generate tags, validate previews, and decide publish actions, which could enable indirect prompt injection.