marketing-seo

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

• Third-party content exposure detected (high risk: 1.00). The skill's Research Mode (Live Competitive Intelligence) in SKILL.md explicitly instructs the agent to use agent-browser to open and scrape public web pages (e.g., "agent-browser open 'https://www.google.com/search?q={target-keyword}'", SimilarWeb, PageSpeed Insights, validator.schema.org, AnswerThePublic) and "agent-browser get text body" to extract SERP, competitor, and technical data that the agent must read and act on, which clearly ingests untrusted third-party content that can influence subsequent recommendations and tool actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's Research Mode depends on installing and running agent-browser via the setup command that fetches code from https://github.com/vercel-labs/agent-browser (npx skills add ...), which clearly downloads and executes remote code as a required dependency.