170-java-documentation
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Maven commands such as
./mvnw validate,./mvnw clean compile, and./mvnw clean verifyto validate project state and documentation. these operations trigger the project's build lifecycle and may execute local tests. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its codebase analysis functionality.
- Ingestion points: Java source files in
src/main/javaare read usingcodebase_searchto generate README and Javadoc content. - Boundary markers: The skill does not define delimiters or instructions to isolate analyzed code from agent logic.
- Capability inventory: The agent can perform file-write operations (README.md, package-info.java) and execute shell commands via Maven.
- Sanitization: No input validation or escaping is applied to the extracted source code content before it is processed by the agent.
Audit Metadata