322-frameworks-spring-boot-testing-integration-tests
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
./mvnw compileand./mvnw clean verify. These commands are used to validate the state of the Java project before and after applying refactoring suggestions. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes user-provided codebase content and executes build tools based on that content.
- Ingestion points: The skill reads Java source files and Maven configuration files (pom.xml) from the project environment.
- Boundary markers: There are no specific delimiters or warnings to the agent to ignore instructions that might be embedded within the processed source code or comments.
- Capability inventory: The skill possesses the capability to execute shell commands via the Maven wrapper, which could be exploited by a malicious project configuration.
- Sanitization: The skill does not implement sanitization or validation of the build configuration or project structure before executing Maven commands.
Audit Metadata