talk-dig

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web searches and fetches full page content using mcp__web-search-prime__webSearchPrime and mcp__web_reader__webReader (references/implementation.md), pulling pages from public sources like arXiv, Google Scholar and university websites and then reading/parsing those pages as part of its paper-analysis workflow, which exposes the agent to untrusted third‑party content that could carry indirect prompt injections.