image-analyzer

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly fetches and analyzes content from arbitrary public URLs (e.g., "Step 1: Get Image from URL", the scrapegraph call with "website_url" in Step 2, and the brand-dev screenshot calls in Step 4), so the agent ingests untrusted third‑party web/user-generated content that can influence parsing and downstream actions.