seo-drift

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow fetches arbitrary page content from a user-supplied <url> via scripts/fetch_page.py and parses it with scripts/parse_html.py, so any free-form HTML/text on that outsider-controlled page can be ingested into the agent’s LLM context (indirect prompt injection risk).