market

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts arbitrary URLs (e.g., /market audit <url>, /market landing <url>, /market seo <url>) and instructs running scripts like scripts/analyze_page.py <url> and to "quote exact strings from the page," so it fetches and interprets open/public web content which can directly influence audit decisions and generated actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs scripts/analyze_page.py at runtime and instructs the agent to quote exact strings from the fetched page, so any arbitrary user-supplied external URL passed as (i.e., the target website fetched by scripts/analyze_page.py) can directly control prompts and outputs.