use-finalrun-cli
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @finalrun/finalrun-agent package from the npm registry, which is the official tool maintained by the skill author.
- [COMMAND_EXECUTION]: The agent uses the finalrun CLI to execute diagnostic, validation, and testing commands within the project repository.
- [PROMPT_INJECTION]: The skill is designed to read and process untrusted data from the repository's .finalrun/ directory, creating a surface for indirect prompt injection. * Ingestion points: Files located in .finalrun/tests/, .finalrun/suites/, .finalrun/env/, and .finalrun/config.yaml. * Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish ingested file content from system instructions. * Capability inventory: The agent has the capability to install global packages and execute shell commands via the finalrun CLI. * Sanitization: The instructions do not specify any validation or sanitization of the file content before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill includes explicit security guidelines for handling sensitive API keys and environment variables, instructing the agent to never guess secrets and to require manual user configuration for credentials.
Audit Metadata