image-prompt-generator

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

• Third-party content exposure detected (high risk: 0.70). The skill's image generation script supports a rework mode that loads arbitrary input images (scripts/generate_image.py --input) and the documentation explicitly describes downloading photos from Telegram (references/styles/schematic.md), so the agent ingests untrusted, user-provided third-party images it is expected to read/interpret.