liferay

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to connect to a Liferay instance via the Membrane CLI and run actions that read/manage user-generated Liferay content (e.g., Blog Posting, Comment, Wiki Page, Message Board Message) as shown in SKILL.md, which exposes the agent to untrusted third-party content that could influence decisions.