The Agent Skills Directory

[Prompt Injection] (SAFE): The prompt uses standard instructional language to define the AI's role as a testing expert. There are no attempts to bypass safety filters or override system instructions.
[Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns were detected. Example emails used in tests are generic (e.g., test@example.com).
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not perform any package installations (npm, pip, etc.) or download/execute remote scripts.
[Obfuscation] (SAFE): All content is in plain text. No Base64, zero-width characters, or hex escapes were found.
[Indirect Prompt Injection] (SAFE): While the skill is designed to process user-provided code to generate tests, it lacks the dangerous capabilities (like file writing or network access) that would make indirect injection a high risk.

test-generator