channel3-api

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly uses the Enrich endpoint (POST /v0/enrich) and image-based search (image_url/base64_image) which accept arbitrary product page or image URLs and perform real-time extraction, meaning the agent fetches and ingests untrusted public third‑party content (product pages/images) that can influence subsequent actions.