nielsen-heuristics-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and instructs the agent to review "screenshots_or_links" (URLs of screenshots, prototypes, or live site/app), which requires fetching and interpreting arbitrary public or user-provided web content and therefore exposes the agent to untrusted third-party content that could carry indirect prompt injections.