421-frameworks-quarkus-testing-unit-tests
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run
./mvnw compileand./mvnw clean verifyto validate project state before and after refactoring. These commands are necessary for the development workflow but execute scripts and code defined within the project's local environment. - [PROMPT_INJECTION]: The skill evaluates project source code and test files to suggest improvements. It lacks explicit boundary markers or instructions to isolate analyzed code from the skill's own logic, creating a surface for indirect prompt injection (Category 8). Evidence: (1) Ingestion points: Local Java source files and unit tests. (2) Boundary markers: Absent in instructions. (3) Capability inventory: Shell execution via Maven commands. (4) Sanitization: Absent.
Audit Metadata