cro

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

• Third-party content exposure detected (high risk: 0.90). The skill's required-context and process steps in SKILL.md explicitly ask for a "Page URL or description" and direct the agent to "Review the page as a first-time visitor" (Standard Landing Page Audit step 1 and Required Context), which indicates the agent will fetch and interpret public third-party web pages and use that content to drive recommendations and test decisions, exposing it to untrusted external content that could carry indirect prompt injections.