java-junit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided Java source code for test creation and review, which creates a potential surface for indirect prompt injection.
- Ingestion points: Java source code and build configuration files (pom.xml, build.gradle) provided by the user and processed in accordance with the JUnit best practices instructions.
- Boundary markers: The skill instructions do not specify any delimiters or safety prompts to ensure the agent ignores instructions that may be hidden within the code being analyzed.
- Capability inventory: The skill workflow includes the execution of build tool commands (mvn test, gradle test) which execute code defined in the project's test suite or build configuration.
- Sanitization: No explicit sanitization or validation steps are provided to check the integrity of the code before processing or execution.
- [EXTERNAL_DOWNLOADS]: The skill includes references to external source repositories managed by well-known organizations.
- Evidence: The CHANGELOG.md references an initial import from the github/awesome-copilot repository, which is a trusted source.
Audit Metadata