The Agent Skills Directory

[SAFE]: The skill instructions do not contain any malicious patterns such as prompt injection, credential exfiltration, or persistence mechanisms. Its functionality is limited to providing text-based feedback on code snippets.
[SAFE]: No external dependencies or remote code execution patterns were detected. The skill does not use the dynamic context injection syntax or any external tools.
[SAFE]: Although the skill processes untrusted user-provided code, it lacks the necessary capabilities (such as file-writing or subprocess execution) to be exploited via indirect prompt injection.

code-critic