newrelic-cli-deployments
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides bash script templates intended for use in CI/CD environments. These scripts invoke the
newrelicCLI tool, passing system environment variables as command-line arguments. - [INDIRECT_PROMPT_INJECTION]: The skill defines automation workflows that ingest data from external sources, such as Git commit titles and user login names, which are then interpolated into CLI commands. This represents a vulnerability surface where maliciously crafted external content could attempt to influence the agent or the underlying shell execution.
- Ingestion points: Environment variables such as
CI_COMMIT_TITLE,CI_COMMIT_SHORT_SHA, andGITLAB_USER_LOGINdefined inSKILL.md. - Boundary markers: None; the templates rely on standard shell quoting to prevent word splitting but do not sanitize the content itself.
- Capability inventory: The skill utilizes the
newrelic apm deployment createcommand to submit data to external observability platforms. - Sanitization: No input validation or sanitization logic is included in the provided script examples.
Audit Metadata