seo-dataforseo

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

• Third-party content exposure detected (high risk: 0.90). This skill calls DataForSEO endpoints that pull open/public third‑party content (search results, YouTube listings, Google Trends) via functions like get_google_serp and get_youtube_serp in scripts/api/serp.py and get_trends_explore in scripts/api/trends.py, and those saved JSON results are read and summarized (SKILL.md "Summarize" phase and main.py workflows) to produce recommendations, so untrusted third‑party content can materially influence agent behavior.