datadog-automation

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes “Search and Analyze Logs” via DATADOG_SEARCH_LOGS, whose runtime response contains outsider-authored free-form log message text (from other systems/users) that the agent will ingest into LLM context for analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting at runtime to the Rube MCP server https://rube.app/mcp to obtain tool schemas (via RUBE_SEARCH_TOOLS), which directly controls available agent tools/instructions and is a required dependency.