claude-automation-recommender

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md and referenced files explicitly instruct the agent to "use web search" and to rely on context7/Exa MCP for live documentation lookup (references/mcp-servers.md and Output Guidelines), meaning the agent is expected to fetch and interpret public third-party web content that can materially influence recommended MCP servers, plugins, and actions.