ingest-content

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

• Third-party content exposure detected (high risk: 0.75). The skill ingests markdown lesson bodies from either content-library/courses/[slug]/, {{PROJECT_ROOT}}/docs/, or a user-provided path, and those markdown files are parsed into HTML/lesson text that is then used for LLM-context processing (i.e., outsider-authored free text from course repositories/files not authored by the operating user).