java-architect
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard build tool commands such as
./mvnw verifyand./gradlew checkto validate project state, security configurations, and test coverage. This is a common and expected behavior for a developer-oriented tool. - [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on GitHub Pages (
https://jeffallan.github.io/claude-skills/skills/language/java-architect/). This is documented as a source for extended guidance and does not involve immediate execution of remote scripts. - [PROMPT_INJECTION]: As a code architect skill, it is designed to ingest and analyze user-provided Java source code, which represents a surface for indirect prompt injection. The skill includes specific instructions to prioritize architecture boundaries and clean code principles, which helps mitigate accidental instruction following from untrusted data inputs.
- [SAFE]: The skill emphasizes security best practices, such as externalizing configuration, using OAuth2/JWT for security, and mandates against storing unencrypted sensitive data.
Audit Metadata