pp-hackernews

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public, user-generated Hacker News content (and Algolia search results) as part of its required workflow—see commands like hackernews-pp-cli sync, stories, items, users, pulse, and repost in SKILL.md—which the agent is expected to read/interpret (JSON via --agent) and which can materially influence decisions (e.g., repost checks, topic pulse, hiring filters).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs installing and running remote code at runtime via "npx -y @mvanhorn/printing-press install hackernews --cli-only" and/or "go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/hackernews/cmd/hackernews-pp-cli@latest", which fetches and executes remote code and is a required dependency for the skill.