The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous examples and bash scripts for executing the newrelic CLI to query telemetry, manage alert policies, and record deployments.
[EXTERNAL_DOWNLOADS]: The documentation references downloading the official New Relic CLI from the organization's public GitHub releases page.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted telemetry data retrieved from New Relic.
Ingestion points: Queries in nrql/SKILL.md and apm/SKILL.md retrieve Log events and TransactionError messages which can contain arbitrary strings provided by external users or systems.
Boundary markers: There are no specific delimiters or instructions defined to isolate telemetry data from the agent's instructions.
Capability inventory: The agent has the capability to execute shell commands via the newrelic CLI, including write operations like modifying alert conditions and policies.
Sanitization: No sanitization or validation of the retrieved telemetry data is performed before it is presented to the agent for analysis.

newrelic-cli-skills