tuzi-skills-bundle

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

• Third-party content exposure detected (high risk: 1.00). The repository explicitly includes utilities that fetch and ingest open web content — e.g., "tuzi-url-to-markdown" (fetch any URL via Chrome CDP and download media) and "tuzi-danger-x-to-markdown" (convert X/Twitter posts to Markdown) as shown in CHANGELOG.md and CLAUDE.md — meaning the agent will read untrusted, user-generated third‑party pages/tweets and use that content in workflows that can change downstream tool actions.