running-smoke-tests
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured to use the Bash tool with the pattern test:smoke-*. This enables the execution of shell commands, which is a powerful capability. While the tool is restricted to a specific naming pattern, the underlying scripts being called are not provided for inspection.
- [DATA_EXFILTRATION]: The skill instructions specify reading from {baseDir}/config/ to examine environment settings. This creates a risk of exposing sensitive data such as API keys or credentials to the agent's context if they are stored within the configuration directory.
- [NO_CODE]: Although the documentation references multiple scripts (run_tests.sh, parse_results.py, setup_env.sh) and asset templates, the actual file contents for these resources are missing from the package. This lack of transparency prevents verification of the logic being executed or the data being processed.
Audit Metadata