ai-daily-digest

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

• Third-party content exposure detected (high risk: 0.95). Step 1 fetches outsider-authored RSS/Atom content from public web feeds (e.g., fetch(feed.xmlUrl)), parses their title/description into JSON, then Step 2/3 uses that text to build AI prompts (buildScoringPrompt / buildSummaryPrompt) that are sent into the agent/LLM context for scoring and summarization.