seo

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow is not specified here; however, it explicitly requires “read the real page first” and “page-specific” auditing, which in practice typically involves fetching and ingesting existing web page text (outsider-authored content) into the agent’s LLM context for analysis.