hn-analysis

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches Hacker News post text and top comments from a public web source at runtime (via WebFetch on the provided news.ycombinator.com/item?id=...), which includes outsider-authored free-form comment text that is then ingested into the agent’s LLM context for analysis.