iopho-product-context

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

• Third-party content exposure detected (high risk: 0.90). The skill's Auto-Detect mode explicitly scrapes a provided "website URL → scrape tagline, features, pricing" (see Mode 2 in SKILL.md) and pre-fills answers from those detected public site contents, which are untrusted third-party data that the agent will read and use to populate context and drive downstream decisions.