423-frameworks-quarkus-testing-acceptance-tests
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform local build and verification steps using Maven (
mvn compile,mvn clean verify) and the Maven Wrapper (./mvnw). These are standard development operations but involve the execution of a build system that manages third-party plugins and project dependencies. - [PROMPT_INJECTION]: The skill implements robust defenses against indirect prompt injection by requiring 'maintainer-sanitized' Gherkin scenario facts. It explicitly commands the agent to treat scenario text, comments, and docstrings as untrusted data and forbids obeying any instructions embedded within that data.
Audit Metadata