alterlab-cdm-postproduction

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires the agent to "Search the web" for editing workflows, color grading references (LUTs), codec specs, and delivery requirements (see Workflow step 1 and Agentic Protocol "Research first"), meaning it ingests untrusted public third‑party web content that the agent must read and that can materially influence its decisions and actions.