The Agent Skills Directory

[PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override agent behavior, bypass safety guidelines, or extract system prompts.
[DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or network operations to non-whitelisted domains were found. The skill focuses entirely on local Java unit testing logic.
[EXTERNAL_DOWNLOADS]: The skill provides configuration snippets for Maven and Gradle using standard, well-known libraries (Spring Boot, JUnit 5, Mockito, AssertJ). There are no scripts that download or execute code from untrusted remote sources.
[COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation (sudo), or persistence mechanisms were detected. The allowed tools are restricted to standard file and search operations.
[OBFUSCATION]: The content is clear and readable. No Base64 encoding, zero-width characters, or homoglyphs were used to hide malicious intent.
[DYNAMIC_EXECUTION]: The skill does not generate or execute code at runtime using unsafe methods like eval, exec, or unsafe deserialization.

unit-test-application-events