seo-and-geo

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflows (e.g., the "Broken Link Outreach Workflow" / references/backlink-hunter.md and the technical-audit steps in SKILL.md) explicitly instruct the agent to run web_search and web_fetch (curl/HEAD requests, fetching robots.txt and arbitrary resource pages, extracting outbound links) and to parse that public, third‑party HTML/content to decide replacements and send outreach, so it ingests untrusted open-web content that can materially influence tool actions.