hatch-pet

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is ingested at runtime as the user’s concept/notes to create prompt text that is then fed into $imagegen for the base and row jobs (via prepare_pet_run.py generating prompts/base-pet.md and scripts/prepare_pet_run.py’s row_prompt() content).