alterlab-cdm-screenwriter

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and Agentic Protocol explicitly instruct the agent to "Search the web for screenplay format standards, dialogue techniques, and structure models" and to "Research first," which means it will fetch and read open/public third-party web content that can influence the agent's decisions and tool use (SKILL.md Workflow step 1 / Agentic Protocol).