ccc-seo

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires fetching and interpreting open web content and third‑party API data as part of its mandatory workflows (e.g., aaio SKILL.md Quick Audit Workflow instructs the agent to run curl -s SITE/robots.txt and curl -sL SITE/ to inspect HTML/JSON/llms.txt/sitemap.md, and backlink-audit SKILL.md requires calling SemRush/Ahrefs API endpoints), and those external findings are used to drive recommendations and actions (disavow files, routing, optimization steps), so untrusted public content can materially influence the agent's decisions and tool use.