optimize-cli-for-agents

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly describes commands that fetch public web content (e.g., "seo-research fetch-pages --source-set current --json" and "fetch the current SERP" in the "Steering Contract" and "Planner-in-the-CLI" sections), and instructs agents to parse that returned guidance/next_actions to decide subsequent commands, so the agent will ingest untrusted third-party pages whose content can materially steer tool use.