agent-add-mcp

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s workflow reads and writes only Warp config files (~/.warp/.mcp.json or {repo_root}/.warp/.mcp.json) and any optional “WebSearch” is used to fetch server configuration details, which would expose the agent to outsider-authored free text from search/web results at runtime.