mcp-integration-reference

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and read issue and event data from an external MCP (see Step 3 "Fetch Error Data" and the tool calls documented in references/sentry-mcp.md such as mcp__sentry-mcp__list_issues / get_issue / get_event), which are untrusted/user-generated third-party contents that the agent must interpret and that can materially influence its analysis and next actions.