llm-wiki

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly defines "Raw Sources" as articles/papers/blogs/forums and references an ingest-url skill and source-quality buckets (e.g., forum, blog) — implying the agent will fetch and process arbitrary public URLs and user-generated web content (from OBSIDIAN_SOURCES_DIR / ingest-url) that can change how the LLM updates the wiki.