mo-book-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory pipeline (Phase 1: "Accept Any of These Inputs" and the pipeline tool-call examples in references/pipeline.md) explicitly accepts and uses URLs pointing to PDFs/text and instructs the agent to fetch and ingest those documents with the pdf tool, meaning untrusted third-party content can be read and directly used to generate decision rules and runtime behavior.