523-frameworks-micronaut-testing-acceptance-tests

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands including ./mvnw compile and ./mvnw clean verify. These are standard project validation steps in a Java development environment and are used to ensure the application state is correct before and after applying changes.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted Gherkin .feature files to influence its code generation and execution logic.
  • Ingestion points: The Gherkin .feature file is a required input for the skill (referenced in SKILL.md and the reference document).
  • Boundary markers: There are no instructions for the agent to use delimiters or specific ignore-instructions logic when reading the feature file content.
  • Capability inventory: The agent has the ability to write new Java classes to the filesystem and execute Maven commands on the project.
  • Sanitization: No input validation or sanitization rules are defined for the text within the Gherkin scenarios before they are used to generate test code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:06 PM