seo-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires including the page's "actual current HTML" and copy-paste-ready replacement code in outputs, which forces the LLM to reproduce any secrets (API keys, tokens, cookies, passwords) present in the page verbatim and so creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses live public web pages using Playwright (playwright-cli open/goto/run-code) and SerpAPI, runs scripts/extract_page_signals.py to ingest the page HTML, and requires including the actual current HTML in the action report—so untrusted third-party page content is read and can directly influence analysis and recommended actions.