to-markdown

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow and fetch layer (SKILL.md and references/fetch.md) explicitly fetch and convert arbitrary public URLs using trafilatura and Playwright and ingest that untrusted, user-provided web content for LLM/RAG pipelines, which can expose the agent to indirect prompt injection.