seo-images

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

• Third-party content exposure detected (high risk: 0.95). Runtime path: the skill uses mcp__firecrawl-mcp__firecrawl_scrape to fetch and parse raw HTML/markdown from a user-supplied target URL (public web content), then ingests outsider-authored <img>/<picture> attributes and <script type="application/ld+json"> text into the agent’s LLM context for analysis.