seo-content

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests arbitrary public webpages as part of its required workflow (see SKILL.md Phase 2 "Fetch & Parse" and scripts/fetch_page.py which performs requests.get on a user-provided URL), so untrusted third‑party content can be read and used to drive analysis and recommendations.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs scripts/fetch_page.py at runtime to fetch a user-supplied URL (e.g., https://example.com/landing) and then feeds the fetched page content into the analysis workflow, so arbitrary remote content can directly control the agent's input/prompts.