web-scraping-hardened

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly tells the agent to monitor network traffic and "document headers, cookies, authentication tokens," which requires capturing and potentially outputting secret values verbatim (exfiltration risk).

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to open arbitrary target websites with Playwright and Chrome DevTools (Phase 1) and to fetch public site files like robots.txt/sitemaps via curl (Phase 2), meaning the agent will ingest and interpret untrusted third‑party web content which directly drives strategy selection and subsequent automated actions.