java-architect
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The core workflow in
SKILL.mdinstructs the agent to execute shell commands such as./mvnw verifyand./gradlew check. These are standard developer operations used to run integration tests, check JaCoCo coverage reports, and verify Spring Security filter chains. - [PROMPT_INJECTION]: The skill contains an Indirect Prompt Injection surface (Category 8):
- Ingestion points: The agent is instructed to review local project structures, dependencies, and Spring configurations (
SKILL.md). - Boundary markers: The skill does not define explicit delimiters to separate untrusted project content from agent instructions.
- Capability inventory: The agent has the capability to execute shell commands via Maven and Gradle wrappers (
SKILL.md). - Sanitization: No specific sanitization or filtering logic is provided for data ingested from the project environment.
- [SAFE]: Security best practices are followed regarding credential management;
references/spring-boot-setup.mdandreferences/spring-security.mduse environment variable placeholders for database passwords and JWT secrets, explicitly warning the user to externalize and change these values in production.
Audit Metadata