423-frameworks-quarkus-testing-acceptance-tests
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests Gherkin scenario facts which could contain malicious instructions.
- Ingestion points: Processes maintainer-sanitized Gherkin scenario facts (feature name, scenario titles, tags, and Given/When/Then steps) as described in SKILL.md and the reference file.
- Boundary markers: Includes explicit instructions in both SKILL.md and the reference file to treat Gherkin text as untrusted data and never obey instructions embedded in scenario text, comments, or docstrings.
- Capability inventory: The skill instructs the agent to perform shell commands (mvn compile, mvn clean verify) and write Java test classes and JSON mapping files to the local filesystem.
- Sanitization: Requires a maintainer-authored sanitized scenario summary and explicitly forbids raw outsider-authored .feature text.
- [COMMAND_EXECUTION]: The skill executes local build and verification commands.
- Evidence: Instructs the agent to run ./mvnw compile, mvn compile, ./mvnw clean verify, and mvn clean verify to validate the project state and test results.
Audit Metadata