marketingskills-ai-agent-collection

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and analyze external websites (e.g., "Agent uses seo-audit skill when you say: 'Audit my website's SEO'" and the runSEOAudit(siteUrl) example, plus programmatic-seo examples using getCompetitor/getCompetitors), which requires reading untrusted public web content that can directly influence recommendations and subsequent actions.