302-frameworks-spring-boot-rest
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 execute shell commands using the Maven wrapper (
./mvnw compile,./mvnw clean verify) to assess project state and verify improvements. These commands are integral to the skill's primary purpose of safe code refactoring. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It processes untrusted data from the project environment, including Java source code and OpenAPI specifications, which could contain malicious directives. The instructions lack explicit boundary markers or sanitization logic to mitigate the risk of the agent following instructions embedded within the files it analyzes.
- Ingestion points: Java source files (controllers, DTOs, entities) and OpenAPI YAML specifications.
- Boundary markers: None identified; instructions do not specify delimiters or directives to ignore embedded instructions.
- Capability inventory: Execution of build tools (
mvnw) which can execute arbitrary code defined in the project's build configuration or test suites. - Sanitization: Absent; the skill relies on the agent's default processing of source code text.
Audit Metadata