finalrun-use-cli
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read and summarize failure artifacts, including
result.json,device.log, andrunner.log. This creates an indirect prompt injection surface where untrusted data from the application under test or device logs could influence agent behavior. - Ingestion points: Artifact files located in the
.finalrun/workspace directory (e.g.,result.json,actions/*.json,device.log). - Boundary markers: None explicitly defined to separate untrusted artifact content from agent instructions.
- Capability inventory: Execution of
finalrunCLI commands for testing and server management. - Sanitization: No specific sanitization of log/result content is mentioned before processing.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
@finalrun/finalrun-agentpackage from the NPM registry to provide the necessary CLI tools for the agent. - [COMMAND_EXECUTION]: The skill uses various shell commands through the
finalrunCLI to perform environment checks (doctor), validate configurations (check), and execute mobile tests (test,suite).
Audit Metadata