geo-tracking-plan

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly requires fetching and validating public third-party websites and auxiliary public materials (e.g., "若可联网，先确认官方域名，再补充官网、产品页、...," in SKILL.md step 2 and the required references/evidence-sourcing-workflow.md), meaning the agent will ingest untrusted public web content (official sites, social media, media pages) and use that content to drive analysis and decisions.