tech-earnings-deepdive

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

• Third-party content exposure detected (high risk: 1.00). The skill's Primary Evidence Collection Standards and module workflows explicitly require ingesting open/public, untrusted user-generated sources—e.g., Glassdoor/Blind employee reviews, G2/AppStore customer reviews, GitHub activity, earnings call transcripts and public web filings—which the agent must read and use to drive valuation, decisions, and action triggers (see "Primary Evidence Collection Standards" and Modules A, D, G, L), enabling indirect prompt-injection from third-party content.