theory-analysis-product-positioning

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

• Third-party content exposure detected (high risk: 0.90). The skill's Input Contract and workflow require ingesting and analyzing evidence_items.content (see references/01-input-and-gate.md and references/00-theory-foundation.md), which explicitly include user-generated sources like social posts and support tickets, so the agent will read untrusted third-party content that can influence its coding and decisions.