Agent Design 2

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and act on external, user-generated content (e.g., "Pattern 3: MCP-Enhanced Workflows" and the "sync-docs" command which use notion-mcp, github-mcp, and a bundled "github-tools" MCP to read PRs, specs, issues, and post to Slack), meaning the agent will ingest untrusted third-party content that can influence its actions.