security-audit

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

• Third-party content exposure detected (high risk: 0.80). The skill includes runtime code that fetches and processes external, public URLs (e.g., isPasswordBreached calling https://api.pwnedpasswords.com/range/${prefix}, the SSRF example that does fetch(req.query.url), and sendWebhook(url, ...) which posts to arbitrary URLs), so it clearly ingests untrusted third‑party content as part of its workflow.