moai-alfred-workflow

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly integrates with external Content/MCP servers (Context7 and GitHub) — see SKILL.md and examples (Context7Integration.search_code_examples and the .mcp.json / reference showing "github" and "context7" MCP servers and use of pr_url) which cause the agent to fetch and interpret public third‑party content (code examples, PRs, docs) that can influence workflow decisions and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's .mcp.json example shows runtime commands that fetch and execute remote packages (e.g., "npx -y @upstash/context7-mcp@latest" and "npx -y @anthropic-ai/mcp-server-github"), which would download and run remote code as part of the Context7 MCP integration that the skill depends on, so this is a runtime external dependency that can execute code.