reference-design

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires reading and extracting evidence from third-party datasheets, application notes, and evaluation schematics ("Evidence Extraction" and "When the datasheet is ambiguous, look for app notes, eval schematics..."), which are open/public external sources the agent must interpret and that can materially influence design actions.