java-refactoring-extract-method
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run project-local build wrappers, specifically
./mvnw(Maven) and./gradlew(Gradle), to execute tests and verify the refactoring. This is the intended primary purpose of the skill to ensure code safety and functional correctness. - [INDIRECT_PROMPT_INJECTION]: The skill processes external Java source code provided by users and possesses the capability to execute shell commands (test runners). This creates a potential surface where malicious instructions could be embedded in the code to be refactored (e.g., within code comments).
- Ingestion points: User-provided Java code block at the end of
SKILL.md. - Boundary markers: None explicitly defined to isolate the input code from the agent's instructions.
- Capability inventory: Shell command execution via project build tools (
./mvnw,./gradlew). - Sanitization: No explicit sanitization or validation of the input source code is defined.
Audit Metadata