newrelic-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data that could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Data is ingested via analyze_entity_logs, list_recent_logs, and NRQL queries targeting Log, Span, and TransactionError event types, as described in SKILL.md and references/nrql-patterns.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data content and control instructions.
  • Capability inventory: The skill includes capabilities to search entities, execute database queries via execute_nrql_query, and generate impact reports.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation of the retrieved log or trace data before it is processed by the agent.
  • [DYNAMIC_EXECUTION]: The skill uses tools to dynamically generate and execute code at runtime.
  • Evidence: The natural_language_to_nrql_query tool in SKILL.md converts plain English requests into NRQL (New Relic Query Language) and executes them against the connected New Relic database. This is the intended core functionality for data analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 07:04 PM