323-frameworks-spring-boot-testing-acceptance-tests
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires running
./mvnw compileand./mvnw clean verify. These commands execute the project's build logic to validate the environment and the generated tests. In the context of a development tool, this is considered intended and safe behavior. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted
.featurefiles to generate Java code. - Ingestion points: Gherkin
.featurefiles from context. - Boundary markers: Absent; the skill relies on the agent's parsing logic.
- Capability inventory: File system writes (test classes) and shell command execution (Maven).
- Sanitization: Absent; the skill directly maps Gherkin steps to code structures.
Audit Metadata