geo-content

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the runtime workflow to “Fetch the target page(s)” and then “Evaluate E-E-A-T” and generate an analysis that includes “Specific passages and pages,” which implies the agent will ingest outsider-authored free text from fetched web pages into the LLM context for assessment.