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, andmvn 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
.featurefiles and uses that data to generate and execute code. - Ingestion points: Reads
.featurefiles from the local context inStep 1of 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 viamvn clean verify. - Sanitization: There is no explicit mention of sanitizing or escaping the content parsed from the
.featurefiles before it is interpolated into test methods and RestAssured assertions.
Audit Metadata