133-java-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 instructs the agent to execute shell commands such as ./mvnw compile, mvn compile, and mvn clean verify. These are standard Maven lifecycle commands used to validate the project and execute the generated integration tests.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from Gherkin .feature files and uses that data to generate and execute code.
  • Ingestion points: Reads .feature files from the local context in Step 1 of the reference guide.
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands within the Gherkin files.
  • Capability inventory: The skill has the capability to write new Java files (BaseAcceptanceTest.java, {FeatureName}AcceptanceTest.java) and execute them via mvn clean verify.
  • Sanitization: There is no explicit mention of sanitizing or escaping the content parsed from the .feature files before it is interpolated into test methods and RestAssured assertions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:06 PM