summarize-hacker-news
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch front-page stories from the public Hacker News Algolia API and to use tool read_webpage to ingest the linked article pages, meaning it will read untrusted public/user-generated web content that can influence article selection, summaries, and the subsequent send_email_to_user action.
Audit Metadata