seo-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow in SKILL.md instructs the agent to fetch and parse arbitrary public URLs (via scripts/fetch-page.py, scripts/check-page.py, scripts/check-site.py and scripts/check-schema.py) and the scripts set llm_review_required so the agent must read and act on untrusted page HTML, robots.txt, sitemap.xml and JSON‑LD from third‑party sites—clearly exposing it to untrusted web content that can influence decisions.