newrelic-cli-apm
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
newrelicCLI andjqto query and format application performance data. These commands are consistent with the skill's stated purpose of observability and triage. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from New Relic telemetry (such as transaction names, error messages, and database statements) which could be influenced by an attacker who has compromised the application being monitored.
- Ingestion points: Data returned from
newrelic nrql queryandnewrelic entity searchcommands is processed by the agent. - Boundary markers: None present; the instructions do not include delimiters or warnings to ignore instructions embedded in the telemetry data.
- Capability inventory: The skill has the ability to execute shell commands via the
newrelicCLI. - Sanitization: No sanitization or validation of the external query output is performed before it enters the agent's context.
Audit Metadata