worker-onboarding

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

• Third-party content exposure detected (high risk: 0.80). The skill's onboarding modules explicitly include a "competitor-research" and "ad-review-flow" (see modules/competitor-research.ts and modules/ad-review-flow.ts in SKILL.md) that reference public services like Google Maps and Lead Pages and generate "quick win" outputs, indicating the agent ingests and acts on untrusted public third-party content (competitor listings/ads) as part of its workflow.