myvibe-publish

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly imports content from arbitrary public URLs (the --url import flow) and fetches tags from the MyVibe hub (node .../fetch-tags.mjs --hub), and its required "Metadata Analysis" step states the agent will read page HTML (title, og:title, first ), README/source code and use that extracted content to generate titles/descriptions/tags that directly influence publish decisions—so untrusted third‑party content is read and acted upon.