hatch-pet

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests the outsider’s conversation/default prompt text to derive --pet-notes/--description/--style-notes and writes them into first-party prompt files consumed by the runtime $imagegen jobs (via prepare_pet_run.py → prompts/base-pet.md and prompts/rows/*.md), creating an indirect prompt-injection exposure path.