502-frameworks-micronaut-rest
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run Maven build commands to ensure project compilation and verification. Specifically, it instructs the use of
./mvnw compileandmvn clean verifyas safety checks before and after refactoring steps in both SKILL.md and the reference guide. - [INDIRECT_PROMPT_INJECTION]: The skill processes project source code and configuration files which could theoretically contain malicious instructions aimed at the agent. Evidence Chain: 1. Ingestion points: Analyzes project controllers, DTOs, and OpenAPI specification files (SKILL.md). 2. Boundary markers: The skill does not define clear delimiters or warnings to ignore instructions embedded in the project files. 3. Capability inventory: The agent is granted the ability to execute shell-based Maven commands. 4. Sanitization: There is no process for filtering or sanitizing the content of the ingested project files.
Audit Metadata