mcp-ops

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

• Third-party content exposure detected (high risk: 0.90). The skill defines and documents tools/resources that fetch and ingest open-web content (e.g., fetch_webpage in references/tool-handlers.md, api://github/{owner}/{repo} in references/resources-prompts.md, and external API/resource examples like get_weather/get_repo_info) which the agent is expected to read and use as part of workflows, so untrusted third-party content can materially influence tool use and decisions.