finalrun-test-and-fix

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill orchestrates the execution of the finalrun CLI tool (including check, test, and suite commands) to validate application behavior. These operations are core to the vendor's intended functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and acts upon data from external sources such as application logs and test execution artifacts.
  • Ingestion points: The agent triages failures by reading result.json, actions/ metadata, device.log, and runner.log.
  • Boundary markers: There are no specific delimiters or instructions defined to isolate the content of these logs from the agent's control logic.
  • Capability inventory: The skill has the capability to modify repository source code and test YAML files, and to invoke further CLI commands via sibling skills (finalrun-generate-test and finalrun-use-cli).
  • Sanitization: No sanitization or verification steps are specified for the log content before it influences code modification decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 10:16 AM