llm-sentry-geo-marketing

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

• Third-party content exposure detected (high risk: 0.80). The skill's Playwright-based monitoring service clearly navigates public AI search sites (e.g., llm_sentry_monitor/providers/deepseek.py visiting https://chat.deepseek.com), extracts untrusted response_text and citation URLs from third-party pages, and then parses and uses those results (calculating SOV, saving records/citations) as part of its workflow, so external content can materially influence metrics and outcomes.