pp-digg

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and parse public Digg HTML and API endpoints and to surface user-generated social-media content (e.g., via commands like "digg-pp-cli feed raw", "search" (/api/search/stories), "posts" which returns X post bodies, "events", "evidence", and "crossref" to HN/Techmeme), so the agent will read untrusted third‑party content that can materially influence its actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires running the installer "npx -y @mvanhorn/printing-press install digg --cli-only", which fetches and executes remote code at install time and is a required dependency for the skill to run.