321-frameworks-spring-boot-testing-unit-tests
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill mandates running shell commands such as
./mvnw compileand./mvnw clean verify. These are standard procedures for verifying Java project integrity and are not considered malicious in the context of a developer tool. - [PROMPT_INJECTION]: The skill ingests and analyzes source code from the project environment, which presents a surface for indirect prompt injection. 1. Ingestion points: 'Read reference and assess project context' step in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The agent can execute shell commands via Maven. 4. Sanitization: Absent.
Audit Metadata