technical-seo-checker

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

• Third-party content exposure detected (high risk: 0.75). The skill ingests outsider-authored free text when it fetches and parses target page content from user-supplied URLs/domains at runtime (e.g., via crawl.py/onpage.py and optional firecrawl.py rendered DOM), which can contain prompt-injection strings embedded in the HTML/body that the agent then includes in its LLM context.