summarize

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context when the required runtime path uses summarize - (stdin) or a file path that was produced from outsider-authored content (e.g., mktg-transcribe piping a transcript, or a firecrawl-scraped article extract) into the summarize CLI, which then sends that text to its LLM backend.