moai-foundation-claude

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly documents installing and loading third‑party plugins and marketplaces from arbitrary URLs and GitHub (e.g., "/plugin install owner/repo", "/plugin install https://github.com/owner/repo.git", "/plugin marketplace add https://..."), enables browser integration ("Enable Chrome"/"Browse this page") and external web access tools (WebFetch, WebSearch, MCP servers), meaning the agent is expected to fetch and interpret untrusted public content (plugin manifests, remote marketplace JSON, web pages) as part of its workflow.