session2-tools

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs Claude to register MCP servers and run subagents to fetch user-generated content from Slack, Notion, and Google Sheets (see references/block2-tool-connection.md and references/block3-parallel-collection.md), and then reads and uses that content to construct briefings and drive subsequent actions, which exposes the agent to untrusted third-party content that could carry indirect prompt injections.