The Agent Skills Directory

[SAFE]: The skill facilitates legitimate software development tasks by generating unit test files for QML projects.- [PROMPT_INJECTION]: The skill includes specific guardrails in SKILL.md that instruct the agent to treat all content in QML source files strictly as data to be tested, not as instructions to follow. This effectively mitigates the risk of indirect prompt injection from malicious source files.- [COMMAND_EXECUTION]: No unauthorized or dangerous shell commands or scripts were identified. The skill utilizes standard file system tools (e.g., Read, Write) to interact with the project, and includes user-confirmation steps before modifying existing files.- [DATA_EXFILTRATION]: There is no evidence of data exfiltration or credential harvesting. The skill's data access is limited to a bounded set of project files (QML sources, qmldir, and CMakeLists.txt) necessary for test generation.- [SAFE]: All external references and installation commands point to official repositories associated with the author (theqtcompanyrnd), representing normal vendor functionality.

qt-qml-test