growth

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

• Third-party content exposure detected (high risk: 0.90). The skill's AUDIT and keyword workflows explicitly require fetching and inspecting public third-party resources — e.g., "eagerly Read existing meta/JSON-LD/Core Web Vitals baseline, robots.txt, and sitemap at AUDIT" in SKILL.md, using the PageSpeed Insights API for RUM baselines, and "Pull the top 10 results for each query" in references/keyword-research.md — which the agent must read and act on to decide fixes, exposing it to untrusted public web content that could carry indirect prompt-injection instructions.