new_relic-automation

Warn

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • REMOTE_CODE_EXECUTION (MEDIUM): The skill utilizes RUBE_REMOTE_WORKBENCH to perform bulk operations, which explicitly mentions using Python-style code patterns like ThreadPoolExecutor and loops to execute tools. This constitutes a dynamic or remote execution environment.
  • EXTERNAL_DOWNLOADS (LOW): The setup requires connecting to an external MCP server at https://rube.app/mcp. This introduces a dependency on an unverified third-party service provider.
  • COMMAND_EXECUTION (LOW): The skill facilitates the execution of various New Relic operations through RUBE_MULTI_EXECUTE_TOOL. While these are defined as tools, the dynamic discovery of schemas from a remote source increases the attack surface.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes data from New Relic (alerts, monitoring data) which could be manipulated by an external attacker to influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 01:43 AM