background-removal

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md shows the agent ingesting images from arbitrary external URLs (e.g., message content/image_url fields and the Batch Processing PRODUCTS list) so it fetches and processes untrusted third-party content (public images) as part of its workflow, which could materially influence processing decisions.