ai-impact-assessment

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 Research (see SKILL.md and references/ai-impact-research.md) explicitly instructs the agent to run targeted WebSearch queries and gather live web sources (URLs) about the user's role and industry, ingesting open/public third‑party content to form the assessment, which directly informs decisions and the mitigation plan.