affiliate-blog-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to run web_search/web_browse on public sites (e.g., "Use web_search to find 2-3 top competitors" and "Use web_search for '[target keyword]' related searches / People Also Ask" in SKILL.md) so the agent will ingest and act on untrusted third‑party web content (G2/Capterra/search results) that can materially influence competitor selection, keywords, pricing, and CTA placement.