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 required workflow and scripts (SKILL.md "Recommended Workflow" step 2 and the provided scripts: scripts/fetch-page.py, scripts/check-page.py, and scripts/check-site.py) fetch and parse arbitrary public URLs and instruct the agent/LLM to read and semantically judge page content (fields with llm_review_required), so untrusted third‑party page content is directly ingested and can change the agent's decisions.