seo-geo

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly asks the user for a URL and its SKILL.md Phase 2 workflow (and accompanying scripts fetch_page.py and parse_html.py) fetches and parses arbitrary public web pages, meaning untrusted third‑party content is ingested 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: 0.80). This skill runs scripts that fetch an arbitrary, user-supplied target URL at runtime (via python3 scripts/fetch_page.py , e.g., https://example.com/landing) and then parses and uses that page content to drive the analysis and recommendations, so external content can directly influence the agent's outputs.