maestro-run-test

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the lifecycle of Maestro tests. This includes cleaning up previous results using rm -rf build/maestro-results, verifying file paths with ls, and executing the test suite via the maestro test command. These commands are local to the environment and serve the primary function of the skill.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from user-provided paths and tool-generated output files.
  • Ingestion points: User-supplied file or directory paths and XML report files found in the build/maestro-results/ directory.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: The skill allows for local file system operations (ls, rm) and execution of the Maestro CLI tool.
  • Sanitization: There is no evidence of path sanitization or validation of the XML report content before it is summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:19 AM
Security Audit — agent-trust-hub — maestro-run-test