spring-boot-engineer
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in SKILL.md prompt the agent to execute build tool commands like
./mvnw testor./gradlew testto verify implementation. These commands are executed within the local project environment.\n- [PROMPT_INJECTION]: The skill possesses an Indirect Prompt Injection surface (Category 8) due to its design of processing untrusted user requirements while having command execution capabilities.\n - Ingestion points: User-provided requirements and design specifications analyzed in the core workflow of SKILL.md.\n
- Boundary markers: Absent. There are no explicit markers or delimiters defined to distinguish between system instructions and untrusted user inputs.\n
- Capability inventory: Build command execution via Maven or Gradle wrappers (
./mvnw,./gradlew) as specified in SKILL.md.\n - Sanitization: Absent. The agent is not instructed to validate or sanitize user input requirements before incorporating them into code generation or test execution processes.\n- [SAFE]: The skill provides security-hardened templates and explicitly prohibits insecure coding practices such as hardcoding credentials or using field injection.\n- [SAFE]: External references to components like Docker images (eclipse-temurin) or Testcontainers (PostgreSQL) in references/cloud.md and references/testing.md point to well-known and reputable service providers.
Audit Metadata