hn-summarize

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow fetches Hacker News story/comment text via the official Hacker News APIs (e.g., https://hn.algolia.com/api/v1/items/OBJECT_ID and .../item/{id}.json), where the comment bodies are authored by non-operating users (outsider HN commenters) and are ingested as readable JSON text fields into the agent’s LLM context.