seo-geo-claude-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and analyzes open web pages (e.g., commands like "/aaron:compete https://competitor.com", "/aaron:audit https://example.com/blog/my-article" and batch/sitemap audits) and documents Tier 2 fetch tools (cURL, Puppeteer, read-only APIs), so the agent will ingest untrusted public third-party content as part of its workflow which can materially influence subsequent actions.