screen-time-api-engineer

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

• Third-party content exposure detected (high risk: 0.70). The skill's evidence inventory (references/evidence/00-source-url-inventory.md) and guidance explicitly instruct the agent to consult public, user-generated sources (e.g., Medium posts and Apple Developer Forum threads) as field notes, so the agent will read/interpret untrusted third‑party content as part of its workflow.