hardware-solution

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow (see SKILL.md steps 4 and 4.5 and references/download-sources.md) requires the agent to fetch and ingest datasheets, procurement pages and EDA footprints from public third-party sites (AllDatasheet, LCSC/立创商城, semiee, SnapEDA, distributor/manufacturer pages and community/拆解 sites), and those untrusted public sources are read and used to drive component selection, downloads, BOM and design decisions—creating a clear vector for indirect prompt injection.